Llama-7b-Chinese 本地推理
基础环境信息（wsl2安装Ubuntu22.04 + miniconda）
使用miniconda搭建环境
(base) :~$ conda create --name Llama-7b-Chinese python=3.10
Channels:
- defaults
Platform: linux-64
Collecting package metadata (repodata.json): done
Solving environment: done
## Package Plan ##
environment location: /home/chop/miniconda3/envs/Llama-7b-Chinese
added / updated specs:
- python=3.10
The following NEW packages will be INSTALLED:
_libgcc_mutex anaconda/pkgs/main/linux-64::_libgcc_mutex-0.1-main
_openmp_mutex anaconda/pkgs/main/linux-64::_openmp_mutex-5.1-1_gnu
bzip2 anaconda/pkgs/main/linux-64::bzip2-1.0.8-h5eee18b_5
ca-certificates anaconda/pkgs/main/linux-64::ca-certificates-2024.3.11-h06a4308_0
ld_impl_linux-64 anaconda/pkgs/main/linux-64::ld_impl_linux-64-2.38-h1181459_1
libffi anaconda/pkgs/main/linux-64::libffi-3.4.4-h6a678d5_0
libgcc-ng anaconda/pkgs/main/linux-64::libgcc-ng-11.2.0-h1234567_1
libgomp anaconda/pkgs/main/linux-64::libgomp-11.2.0-h1234567_1
libstdcxx-ng anaconda/pkgs/main/linux-64::libstdcxx-ng-11.2.0-h1234567_1
libuuid anaconda/pkgs/main/linux-64::libuuid-1.41.5-h5eee18b_0
ncurses anaconda/pkgs/main/linux-64::ncurses-6.4-h6a678d5_0
openssl anaconda/pkgs/main/linux-64::openssl-3.0.13-h7f8727e_0
pip anaconda/pkgs/main/linux-64::pip-23.3.1-py310h06a4308_0
python anaconda/pkgs/main/linux-64::python-3.10.14-h955ad1f_0
readline anaconda/pkgs/main/linux-64::readline-8.2-h5eee18b_0
setuptools anaconda/pkgs/main/linux-64::setuptools-68.2.2-py310h06a4308_0
sqlite anaconda/pkgs/main/linux-64::sqlite-3.41.2-h5eee18b_0
tk anaconda/pkgs/main/linux-64::tk-8.6.12-h1ccaba5_0
tzdata anaconda/pkgs/main/noarch::tzdata-2024a-h04d1e81_0
wheel anaconda/pkgs/main/linux-64::wheel-0.41.2-py310h06a4308_0
xz anaconda/pkgs/main/linux-64::xz-5.4.6-h5eee18b_0
zlib anaconda/pkgs/main/linux-64::zlib-1.2.13-h5eee18b_0
Proceed ([y]/n)? y
Downloading and Extracting Packages:
Preparing transaction: done
Verifying transaction: done
Executing transaction: done
#
# To activate this environment, use
#
# $ conda activate Llama-7b-Chinese
#
# To deactivate an active environment, use
#
# $ conda deactivate
(base) :~$ conda activate Llama-7b-Chinese
下载llama.cpp
(Llama-7b-Chinese) :~/newmodels$git init
(Llama-7b-Chinese) :~/newmodels$ git clone https://github.com/ggerganov/llama.cpp.git
(Llama-7b-Chinese) :~/newmodels$ cd llama.cpp/
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ ls
CMakeLists.txt common.o ggml-backend.c ggml-sycl.h llama.o sampling.o
LICENSE console.o ggml-backend.h ggml-vulkan-shaders.hpp llama2-tuili.py save-load-state
Makefile convert-hf-to-gguf.py ggml-backend.o ggml-vulkan.cpp llava-cli scripts
Package.swift convert-llama-ggml-to-gguf.py ggml-cuda.cu ggml-vulkan.h lookahead server
README-Origin.md convert-llama2c-to-ggml ggml-cuda.h ggml.c lookup simple
README-sycl.md convert-lora-to-ggml.py ggml-cuda.o ggml.h main speculative
README.md convert-persimmon-to-gguf.py ggml-impl.h ggml.o main.log spm-headers
SHA256SUMS convert.py ggml-kompute.cpp ggml_vk_generate_shaders.py media stage_1_convert.sh
awq-py direct_trainsformers.py ggml-kompute.h gguf models stage_5_test_token.sh
baby-llama docs ggml-metal.h gguf-py mypy.ini tests
batched embedding ggml-metal.m grammar-parser.o parallel tokenize
batched-bench examples ggml-metal.metal grammars passkey train-text-from-scratch
beam-search export-lora ggml-mpi.c imatrix perplexity train.o
benchmark-matmult finetune ggml-mpi.h infill pocs unicode.h
build-info.o flake.lock ggml-opencl.cpp kompute prompts vdot
build.zig flake.nix ggml-opencl.h kompute-shaders q8dot zh-models
ci ggml-alloc.c ggml-quants.c libllava.a quantize
cmake ggml-alloc.h ggml-quants.h llama-bench quantize-stats
codecov.yml ggml-alloc.o ggml-quants.o llama.cpp requirements
common ggml-backend-impl.h ggml-sycl.cpp llama.h requirements.txt
(Llama-7b-Chinese) :~/newmodels/llama.cpp$
安装所需要的软件包
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ ls
AUTHORS convert-hf-to-gguf.py ggml-common.h ggml-vulkan.h llava-cli retrieval
CMakeLists.txt convert-llama-ggml-to-gguf.py ggml-cuda ggml.c lookahead sampling.o
LICENSE convert-llama2c-to-ggml ggml-cuda.cu ggml.h lookup save-load-state
Makefile convert-lora-to-ggml.py ggml-cuda.h ggml.o lookup-create scripts
Package.swift convert-persimmon-to-gguf.py ggml-impl.h ggml_vk_generate_shaders.py lookup-merge server
README-sycl.md convert.py ggml-kompute.cpp gguf lookup-stats sgemm.cpp
README.md docs ggml-kompute.h gguf-py main sgemm.h
SECURITY.md embedding ggml-metal.h gguf-split media simple
baby-llama eval-callback ggml-metal.m grammar-parser.o models speculative
batched examples ggml-metal.metal grammars mypy.ini spm-headers
batched-bench export-lora ggml-mpi.c gritlm ngram-cache.o tests
beam-search finetune ggml-mpi.h imatrix parallel tokenize
benchmark-matmult flake.lock ggml-opencl.cpp infill passkey train-text-from-scratch
build-info.o flake.nix ggml-opencl.h json-schema-to-grammar.o perplexity train.o
build.zig ggml-alloc.c ggml-quants.c kompute pocs unicode-data.cpp
ci ggml-alloc.h ggml-quants.h kompute-shaders prompts unicode-data.h
cmake ggml-alloc.o ggml-quants.o libllava.a q8dot unicode-data.o
codecov.yml ggml-backend-impl.h ggml-sycl.cpp llama-bench quantize unicode.cpp
common ggml-backend.c ggml-sycl.h llama.cpp quantize-stats unicode.h
common.o ggml-backend.h ggml-vulkan-shaders.hpp llama.h requirements unicode.o
console.o ggml-backend.o ggml-vulkan.cpp llama.o requirements.txt vdot
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$ pip install -r requirements.txt
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting numpy~=1.24.4 (from -r ./requirements/requirements-convert.txt (line 1))
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/10/be/ae5bf4737cb79ba437879915791f6f26d92583c738d7d960ad94e5c36adf/numpy-1.24.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.3/17.3 MB 3.5 MB/s eta 0:00:00
Collecting sentencepiece~=0.1.98 (from -r ./requirements/requirements-convert.txt (line 2))
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/7f/e5/323dc813b3e1339305f888d035e2f3725084fc4dcf051995b366dd26cc90/sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 2.8 MB/s eta 0:00:00
Requirement already satisfied: transformers<5.0.0,>=4.35.2 in /home/chop/.local/lib/python3.10/site-packages (from -r ./requirements/requirements-convert.txt (line 3)) (4.39.0)
Collecting gguf>=0.1.0 (from -r ./requirements/requirements-convert.txt (line 4))
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/97/a4/83969343abb00fe787de5965c5c1f617aa51b2e2c563d4391c402aba548f/gguf-0.6.0-py3-none-any.whl (23 kB)
Collecting protobuf<5.0.0,>=4.21.0 (from -r ./requirements/requirements-convert.txt (line 5))
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/15/db/7f731524fe0e56c6b2eb57d05b55d3badd80ef7d1f1ed59db191b2fdd8ab/protobuf-4.25.3-cp37-abi3-manylinux2014_x86_64.whl (294 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 294.6/294.6 kB 2.0 MB/s eta 0:00:00
Collecting torch~=2.1.1 (from -r ./requirements/requirements-convert-hf-to-gguf.txt (line 2))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/03/f1/13137340776dd5d5bcfd2574c9c6dfcc7618285035cd77240496e5c1a79b/torch-2.1.2-cp310-cp310-manylinux1_x86_64.whl (670.2 MB)
Collecting einops~=0.7.0 (from -r ./requirements/requirements-convert-hf-to-gguf.txt (line 3))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/29/0b/2d1c0ebfd092e25935b86509a9a817159212d82aa43d7fb07eca4eeff2c2/einops-0.7.0-py3-none-any.whl (44 kB)
Requirement already satisfied: filelock in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (3.13.4)
Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (0.22.2)
Requirement already satisfied: packaging>=20.0 in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (24.0)
Collecting pyyaml>=5.1 (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/29/61/bf33c6c85c55bc45a29eee3195848ff2d518d84735eb0e2d8cb42e0d285e/PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (705 kB)
Requirement already satisfied: regex!=2019.12.17 in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (2024.4.16)
Requirement already satisfied: requests in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (2.31.0)
Requirement already satisfied: tokenizers<0.19,>=0.14 in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (0.15.2)
Requirement already satisfied: safetensors>=0.4.1 in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (0.4.3)
Requirement already satisfied: tqdm>=4.27 in /home/chop/.local/lib/python3.10/site-packages (from transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (4.66.2)
Requirement already satisfied: typing-extensions in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (4.11.0)
Requirement already satisfied: sympy in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (1.12)
Requirement already satisfied: networkx in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (3.3)
Requirement already satisfied: jinja2 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (3.1.3)
Requirement already satisfied: fsspec in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (2024.3.1)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.1.105)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.1.105)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.1.105)
Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (8.9.2.26)
Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.1.3.1)
Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (11.0.2.54)
Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (10.3.2.106)
Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (11.4.5.107)
Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.1.0.106)
Collecting nvidia-nccl-cu12==2.18.1 (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/a4/05/23f8f38eec3d28e4915725b233c24d8f1a33cb6540a882f7b54be1befa02/nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl (209.8 MB)
Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /home/chop/.local/lib/python3.10/site-packages (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.1.105)
Collecting triton==2.1.0 (from torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/4d/22/91a8af421c8a8902dde76e6ef3db01b258af16c53d81e8c0d0dc13900a9e/triton-2.1.0-0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (89.2 MB)
Requirement already satisfied: nvidia-nvjitlink-cu12 in /home/chop/.local/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (12.4.127)
Requirement already satisfied: MarkupSafe>=2.0 in /home/chop/.local/lib/python3.10/site-packages (from jinja2->torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (2.1.5)
Requirement already satisfied: charset-normalizer<4,>=2 in /home/chop/.local/lib/python3.10/site-packages (from requests->transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /home/chop/.local/lib/python3.10/site-packages (from requests->transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /home/chop/.local/lib/python3.10/site-packages (from requests->transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (2.2.1)
Requirement already satisfied: certifi>=2017.4.17 in /home/chop/.local/lib/python3.10/site-packages (from requests->transformers<5.0.0,>=4.35.2->-r ./requirements/requirements-convert.txt (line 3)) (2024.2.2)
Requirement already satisfied: mpmath>=0.19 in /home/chop/.local/lib/python3.10/site-packages (from sympy->torch~=2.1.1->-r ./requirements/requirements-convert-hf-to-gguf.txt (line 2)) (1.3.0)
Installing collected packages: sentencepiece, triton, pyyaml, protobuf, nvidia-nccl-cu12, numpy, einops, gguf, torch
Attempting uninstall: sentencepiece
Found existing installation: sentencepiece 0.2.0
Uninstalling sentencepiece-0.2.0:
Successfully uninstalled sentencepiece-0.2.0
Attempting uninstall: protobuf
Found existing installation: protobuf 5.26.1
Uninstalling protobuf-5.26.1:
Successfully uninstalled protobuf-5.26.1
Attempting uninstall: numpy
Found existing installation: numpy 1.26.4
Uninstalling numpy-1.26.4:
Successfully uninstalled numpy-1.26.4
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
matplotlib 3.8.4 requires pyparsing>=2.3.1, which is not installed.
tensorboard 2.16.2 requires six>1.9, which is not installed.
Successfully installed einops-0.7.0 gguf-0.6.0 numpy-1.24.4 nvidia-nccl-cu12-2.18.1 protobuf-4.25.3 pyyaml-6.0.1 sentencepiece-0.1.99 torch-2.1.2 triton-2.1.0
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$ pip install pyparsing
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting pyparsing
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/9d/ea/6d76df31432a0e6fdf81681a895f009a4bb47b3c39036db3e1b528191d52/pyparsing-3.1.2-py3-none-any.whl (103 kB)
Installing collected packages: pyparsing
Successfully installed pyparsing-3.1.2
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$ pip install matplotlib
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: matplotlib in /home/chop/.local/lib/python3.10/site-packages (3.8.4)
Requirement already satisfied: contourpy>=1.0.1 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (1.2.1)
Requirement already satisfied: cycler>=0.10 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (4.51.0)
Requirement already satisfied: kiwisolver>=1.3.1 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (1.4.5)
Requirement already satisfied: numpy>=1.21 in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (from matplotlib) (1.24.4)
Requirement already satisfied: packaging>=20.0 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (24.0)
Requirement already satisfied: pillow>=8 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (10.3.0)
Requirement already satisfied: pyparsing>=2.3.1 in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (from matplotlib) (3.1.2)
Requirement already satisfied: python-dateutil>=2.7 in /home/chop/.local/lib/python3.10/site-packages (from matplotlib) (2.9.0.post0)
Collecting six>=1.5 (from python-dateutil>=2.7->matplotlib)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d9/5a/e7c31adbe875f2abbb91bd84cf2dc52d792b5a01506781dbcf25c91daf11/six-1.16.0-py2.py3-none-any.whl (11 kB)
Installing collected packages: six
Successfully installed six-1.16.0
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$ pip install six
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: six in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (1.16.0)
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$ pip install tensorboard
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: tensorboard in /home/chop/.local/lib/python3.10/site-packages (2.16.2)
Requirement already satisfied: absl-py>=0.4 in /home/chop/.local/lib/python3.10/site-packages (from tensorboard) (2.1.0)
Requirement already satisfied: grpcio>=1.48.2 in /home/chop/.local/lib/python3.10/site-packages (from tensorboard) (1.62.2)
Requirement already satisfied: markdown>=2.6.8 in /home/chop/.local/lib/python3.10/site-packages (from tensorboard) (3.6)
Requirement already satisfied: numpy>=1.12.0 in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (from tensorboard) (1.24.4)
Requirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (from tensorboard) (4.25.3)
Requirement already satisfied: setuptools>=41.0.0 in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (from tensorboard) (68.2.2)
Requirement already satisfied: six>1.9 in /home/chop/miniconda3/envs/Llama-7b-Chinese/lib/python3.10/site-packages (from tensorboard) (1.16.0)
Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /home/chop/.local/lib/python3.10/site-packages (from tensorboard) (0.7.2)
Requirement already satisfied: werkzeug>=1.0.1 in /home/chop/.local/lib/python3.10/site-packages (from tensorboard) (3.0.2)
Requirement already satisfied: MarkupSafe>=2.1.1 in /home/chop/.local/lib/python3.10/site-packages (from werkzeug>=1.0.1->tensorboard) (2.1.5)
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$ pip list
Package Version
------------------------- -----------
absl-py 2.1.0
accelerate 0.27.2
aiofiles 23.2.1
aiohttp 3.9.5
aiosignal 1.3.1
altair 5.3.0
annotated-types 0.6.0
anyio 4.3.0
async-timeout 4.0.3
attrs 23.2.0
bitsandbytes 0.42.0
certifi 2024.2.2
charset-normalizer 3.3.2
click 8.1.7
contourpy 1.2.1
cycler 0.12.1
datasets 2.19.0
dill 0.3.8
einops 0.7.0
evaluate 0.4.1
exceptiongroup 1.2.1
fastapi 0.110.2
ffmpy 0.3.2
filelock 3.13.4
fonttools 4.51.0
frozenlist 1.4.1
fsspec 2024.3.1
gekko 1.0.6
gguf 0.6.0
gradio 4.27.0
gradio_client 0.15.1
grpcio 1.62.2
h11 0.14.0
httpcore 1.0.5
httpx 0.27.0
huggingface-hub 0.22.2
idna 3.7
importlib_resources 6.4.0
iniconfig 2.0.0
Jinja2 3.1.3
joblib 1.4.0
jsonschema 4.21.1
jsonschema-specifications 2023.12.1
kiwisolver 1.4.5
Markdown 3.6
markdown-it-py 3.0.0
MarkupSafe 2.1.5
matplotlib 3.8.4
mdurl 0.1.2
mpmath 1.3.0
multidict 6.0.5
multiprocess 0.70.16
networkx 3.3
numpy 1.24.4
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 8.9.2.26
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-nccl-cu12 2.18.1
nvidia-nvjitlink-cu12 12.4.127
nvidia-nvtx-cu12 12.1.105
orjson 3.10.1
packaging 24.0
pandas 2.2.2
peft 0.8.2
pillow 10.3.0
pip 23.3.1
pluggy 1.5.0
protobuf 4.25.3
psutil 5.9.8
pyarrow 16.0.0
pyarrow-hotfix 0.6
pydantic 2.7.0
pydantic_core 2.18.1
pydub 0.25.1
Pygments 2.17.2
pyparsing 3.1.2
pytest 8.1.1
python-dateutil 2.9.0.post0
python-multipart 0.0.9
pytz 2024.1
PyYAML 6.0.1
referencing 0.34.0
regex 2024.4.16
requests 2.31.0
responses 0.18.0
rich 13.7.1
rpds-py 0.18.0
ruff 0.4.1
safetensors 0.4.3
scikit-learn 1.4.2
scipy 1.13.0
semantic-version 2.10.0
sentencepiece 0.1.99
setuptools 68.2.2
shellingham 1.5.4
six 1.16.0
sniffio 1.3.1
starlette 0.37.2
sympy 1.12
tensorboard 2.16.2
tensorboard-data-server 0.7.2
threadpoolctl 3.4.0
tokenizers 0.15.2
tomli 2.0.1
tomlkit 0.12.0
toolz 0.12.1
torch 2.1.2
torchdata 0.7.1
tqdm 4.66.2
transformers 4.39.0
triton 2.1.0
typer 0.12.3
typing_extensions 4.11.0
tzdata 2024.1
urllib3 2.2.1
uvicorn 0.29.0
websockets 11.0.3
Werkzeug 3.0.2
wheel 0.41.2
xxhash 3.4.1
yarl 1.9.4
(Llama-7b-Chinese) :~/Chinese-LLaMA-Alpaca/llama.cpp$
llama.cpp编译
使用GPU编译：
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ make LLAMA_CUBLAS=1 LLAMA_CUDA_NVCC=/usr/local/cuda/bin/nvcc
I llama.cpp build info:
I UNAME_S: Linux
I UNAME_P: x86_64
I UNAME_M: x86_64
I CFLAGS: -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -Wdouble-promotion
I CXXFLAGS: -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi
I NVCCFLAGS: -use_fast_math --forward-unknown-to-host-compiler -arch=native -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128
I LDFLAGS: -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
I CC: cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
I CXX: g++ (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
cc -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -Wdouble-promotion -c ggml.c -o ggml.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c llama.cpp -o llama.o
llama.cpp:7101:26: warning: no previous declaration for ‘std::vector<std::__cxx11::basic_string<char> > splitString(const string&, const std::vector<std::__cxx11::basic_string<char> >&)’ [-Wmissing-declarations]
7101 | std::vector<std::string> splitString(const std::string& input, const std::vector<std::string>& delimiters) {
| ^~~~~~~~~~~
llama.cpp: In function ‘std::vector<std::__cxx11::basic_string<char> > splitString(const string&, const std::vector<std::__cxx11::basic_string<char> >&)’:
llama.cpp:7104:12: warning: unused variable ‘foundPos’ [-Wunused-variable]
7104 | size_t foundPos = 0;
| ^~~~~~~~
llama.cpp: At global scope:
llama.cpp:7134:6: warning: no previous declaration for ‘bool is_spectial_token(const string&, const std::vector<std::__cxx11::basic_string<char> >&)’ [-Wmissing-declarations]
7134 | bool is_spectial_token(const std::string & text, const std::vector<std::string>& delimiters) {
| ^~~~~~~~~~~~~~~~~
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c common/common.cpp -o common.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c common/sampling.cpp -o sampling.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c common/grammar-parser.cpp -o grammar-parser.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c common/build-info.cpp -o build-info.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c common/console.cpp -o console.o
/usr/local/cuda/bin/nvcc -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -use_fast_math --forward-unknown-to-host-compiler -arch=native -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -Wno-pedantic -Xcompiler "-Wno-array-bounds -Wno-format-truncation -Wextra-semi" -c ggml-cuda.cu -o ggml-cuda.o
cc -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -Wdouble-promotion -c ggml-alloc.c -o ggml-alloc.o
cc -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -Wdouble-promotion -c ggml-backend.c -o ggml-backend.o
cc -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -Wdouble-promotion -c ggml-quants.c -o ggml-quants.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/main/main.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o console.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o main -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
==== Run ./main -h for help. ====
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/quantize/quantize.cpp build-info.o ggml.o llama.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o quantize -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/quantize-stats/quantize-stats.cpp build-info.o ggml.o llama.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o quantize-stats -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/perplexity/perplexity.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o perplexity -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/imatrix/imatrix.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o imatrix -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/embedding/embedding.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o embedding -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi pocs/vdot/vdot.cpp ggml.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o vdot -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi pocs/vdot/q8dot.cpp ggml.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o q8dot -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -c common/train.cpp -o train.o
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/train-text-from-scratch/train-text-from-scratch.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o train.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o train-text-from-scratch -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp ggml.o llama.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o convert-llama2c-to-ggml -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/simple/simple.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o simple -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/batched/batched.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o batched -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/batched-bench/batched-bench.cpp build-info.o ggml.o llama.o common.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o batched-bench -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/save-load-state/save-load-state.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o save-load-state -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -Iexamples/server examples/server/server.cpp examples/llava/clip.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o server -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib -Wno-cast-qual
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/gguf/gguf.cpp ggml.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o gguf -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/llama-bench/llama-bench.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o llama-bench -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -static -fPIC -c examples/llava/llava.cpp -o libllava.a -Wno-cast-qual
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/llava/llava-cli.cpp examples/llava/clip.cpp examples/llava/llava.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o llava-cli -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib -Wno-cast-qual
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/baby-llama/baby-llama.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o train.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o baby-llama -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/beam-search/beam-search.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o beam-search -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/speculative/speculative.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o speculative -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/infill/infill.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o console.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o infill -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/tokenize/tokenize.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o tokenize -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/benchmark/benchmark-matmult.cpp build-info.o ggml.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o benchmark-matmult -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/parallel/parallel.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o parallel -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/finetune/finetune.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o train.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o finetune -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/export-lora/export-lora.cpp ggml.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o export-lora -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/lookahead/lookahead.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o lookahead -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/lookup/lookup.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o lookup -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
g++ -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi examples/passkey/passkey.cpp ggml.o llama.o common.o sampling.o grammar-parser.o build-info.o ggml-cuda.o ggml-alloc.o ggml-backend.o ggml-quants.o -o passkey -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
cc -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -Wdouble-promotion -c tests/test-c.c -o tests/test-c.o
(Llama-7b-Chinese) :~/newmodels/llama.cpp$
下载模型：Llama-7b-Chinese
你可以从以下来源下载Llama-7b-Chinese模型。
https://github.com/LlamaFamily/Llama-Chinese?tab=readme-ov-file
(Llama-7b-Chinese) :~/Llama-7b-Chinese$ ls
Llama2中文社区.jpeg checklist.chk consolidated.00.pth params.json tokenizer.model tokenizer_config.json
Llama2中文社区.txt config.json generation_config.json special_tokens_map.json tokenizer_checklist.chk
模型复制
将模型复制到llama.cpp的models目录下
(Llama-7b-Chinese) :~$ cp Llama-7b-Chinese ./newmodels/llama.cpp/models/
(Llama-7b-Chinese) :~/newmodels/llama.cpp/models$ ls
Llama-7b-Chinese ggml-vocab-falcon.gguf ggml-vocab-llama.gguf ggml-vocab-stablelm-3b-4e1t.gguf
ggml-vocab-aquila.gguf ggml-vocab-gpt-neox.gguf ggml-vocab-mpt.gguf ggml-vocab-starcoder.gguf
ggml-vocab-baichuan.gguf ggml-vocab-gpt2.gguf ggml-vocab-refact.gguf
模型转换
手动转换模型文件为GGUF格式
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ python convert.py models/Llama-7b-Chinese/
Loading model file models/Llama-7b-Chinese/consolidated.00.pth
params = Params(n_vocab=32000, n_embd=4096, n_layer=32, n_ctx=2048, n_ff=11008, n_head=32, n_head_kv=32, n_experts=None, n_experts_used=None, f_norm_eps=1e-05, rope_scaling_type=None, f_rope_freq_base=None, f_rope_scale=None, n_orig_ctx=None, rope_finetuned=None, ftype=None, path_model=PosixPath('models/Llama-7b-Chinese'))
Found vocab files: {'tokenizer.model': PosixPath('models/Llama-7b-Chinese/tokenizer.model'), 'vocab.json': None, 'tokenizer.json': None}
Loading vocab file 'models/Llama-7b-Chinese/tokenizer.model', type 'spm'
Vocab info: <SentencePieceVocab with 32000 base tokens and 0 added tokens>
Special vocab info: <SpecialVocab with 0 merges, special tokens {'bos': 1, 'eos': 2, 'pad': 0}, add special tokens {'bos': True, 'eos': False}>
tok_embeddings.weight -> token_embd.weight | BF16 | [32000, 4096]
norm.weight -> output_norm.weight | BF16 | [4096]
output.weight -> output.weight | BF16 | [32000, 4096]
layers.0.attention.wq.weight -> blk.0.attn_q.weight | BF16 | [4096, 4096]
layers.0.attention.wk.weight -> blk.0.attn_k.weight | BF16 | [4096, 4096]
layers.0.attention.wv.weight -> blk.0.attn_v.weight | BF16 | [4096, 4096]
layers.0.attention.wo.weight -> blk.0.attn_output.weight | BF16 | [4096, 4096]
layers.0.feed_forward.w1.weight -> blk.0.ffn_gate.weight | BF16 | [11008, 4096]
layers.0.feed_forward.w2.weight -> blk.0.ffn_down.weight | BF16 | [4096, 11008]
layers.0.feed_forward.w3.weight -> blk.0.ffn_up.weight | BF16 | [11008, 4096]
layers.0.attention_norm.weight -> blk.0.attn_norm.weight | BF16 | [4096]
layers.0.ffn_norm.weight -> blk.0.ffn_norm.weight | BF16 | [4096]
layers.1.attention.wq.weight -> blk.1.attn_q.weight | BF16 | [4096, 4096]
layers.1.attention.wk.weight -> blk.1.attn_k.weight | BF16 | [4096, 4096]
layers.1.attention.wv.weight -> blk.1.attn_v.weight | BF16 | [4096, 4096]
layers.1.attention.wo.weight -> blk.1.attn_output.weight | BF16 | [4096, 4096]
layers.1.feed_forward.w1.weight -> blk.1.ffn_gate.weight | BF16 | [11008, 4096]
layers.1.feed_forward.w2.weight -> blk.1.ffn_down.weight | BF16 | [4096, 11008]
layers.1.feed_forward.w3.weight -> blk.1.ffn_up.weight | BF16 | [11008, 4096]
layers.1.attention_norm.weight -> blk.1.attn_norm.weight | BF16 | [4096]
layers.1.ffn_norm.weight -> blk.1.ffn_norm.weight | BF16 | [4096]
layers.2.attention.wq.weight -> blk.2.attn_q.weight | BF16 | [4096, 4096]
layers.2.attention.wk.weight -> blk.2.attn_k.weight | BF16 | [4096, 4096]
layers.2.attention.wv.weight -> blk.2.attn_v.weight | BF16 | [4096, 4096]
layers.2.attention.wo.weight -> blk.2.attn_output.weight | BF16 | [4096, 4096]
layers.2.feed_forward.w1.weight -> blk.2.ffn_gate.weight | BF16 | [11008, 4096]
layers.2.feed_forward.w2.weight -> blk.2.ffn_down.weight | BF16 | [4096, 11008]
layers.2.feed_forward.w3.weight -> blk.2.ffn_up.weight | BF16 | [11008, 4096]
layers.2.attention_norm.weight -> blk.2.attn_norm.weight | BF16 | [4096]
layers.2.ffn_norm.weight -> blk.2.ffn_norm.weight | BF16 | [4096]
layers.3.attention.wq.weight -> blk.3.attn_q.weight | BF16 | [4096, 4096]
layers.3.attention.wk.weight -> blk.3.attn_k.weight | BF16 | [4096, 4096]
layers.3.attention.wv.weight -> blk.3.attn_v.weight | BF16 | [4096, 4096]
layers.3.attention.wo.weight -> blk.3.attn_output.weight | BF16 | [4096, 4096]
layers.3.feed_forward.w1.weight -> blk.3.ffn_gate.weight | BF16 | [11008, 4096]
layers.3.feed_forward.w2.weight -> blk.3.ffn_down.weight | BF16 | [4096, 11008]
layers.3.feed_forward.w3.weight -> blk.3.ffn_up.weight | BF16 | [11008, 4096]
layers.3.attention_norm.weight -> blk.3.attn_norm.weight | BF16 | [4096]
layers.3.ffn_norm.weight -> blk.3.ffn_norm.weight | BF16 | [4096]
layers.4.attention.wq.weight -> blk.4.attn_q.weight | BF16 | [4096, 4096]
layers.4.attention.wk.weight -> blk.4.attn_k.weight | BF16 | [4096, 4096]
layers.4.attention.wv.weight -> blk.4.attn_v.weight | BF16 | [4096, 4096]
layers.4.attention.wo.weight -> blk.4.attn_output.weight | BF16 | [4096, 4096]
layers.4.feed_forward.w1.weight -> blk.4.ffn_gate.weight | BF16 | [11008, 4096]
layers.4.feed_forward.w2.weight -> blk.4.ffn_down.weight | BF16 | [4096, 11008]
layers.4.feed_forward.w3.weight -> blk.4.ffn_up.weight | BF16 | [11008, 4096]
layers.4.attention_norm.weight -> blk.4.attn_norm.weight | BF16 | [4096]
layers.4.ffn_norm.weight -> blk.4.ffn_norm.weight | BF16 | [4096]
layers.5.attention.wq.weight -> blk.5.attn_q.weight | BF16 | [4096, 4096]
layers.5.attention.wk.weight -> blk.5.attn_k.weight | BF16 | [4096, 4096]
layers.5.attention.wv.weight -> blk.5.attn_v.weight | BF16 | [4096, 4096]
layers.5.attention.wo.weight -> blk.5.attn_output.weight | BF16 | [4096, 4096]
layers.5.feed_forward.w1.weight -> blk.5.ffn_gate.weight | BF16 | [11008, 4096]
layers.5.feed_forward.w2.weight -> blk.5.ffn_down.weight | BF16 | [4096, 11008]
layers.5.feed_forward.w3.weight -> blk.5.ffn_up.weight | BF16 | [11008, 4096]
layers.5.attention_norm.weight -> blk.5.attn_norm.weight | BF16 | [4096]
layers.5.ffn_norm.weight -> blk.5.ffn_norm.weight | BF16 | [4096]
layers.6.attention.wq.weight -> blk.6.attn_q.weight | BF16 | [4096, 4096]
layers.6.attention.wk.weight -> blk.6.attn_k.weight | BF16 | [4096, 4096]
layers.6.attention.wv.weight -> blk.6.attn_v.weight | BF16 | [4096, 4096]
layers.6.attention.wo.weight -> blk.6.attn_output.weight | BF16 | [4096, 4096]
layers.6.feed_forward.w1.weight -> blk.6.ffn_gate.weight | BF16 | [11008, 4096]
layers.6.feed_forward.w2.weight -> blk.6.ffn_down.weight | BF16 | [4096, 11008]
layers.6.feed_forward.w3.weight -> blk.6.ffn_up.weight | BF16 | [11008, 4096]
layers.6.attention_norm.weight -> blk.6.attn_norm.weight | BF16 | [4096]
layers.6.ffn_norm.weight -> blk.6.ffn_norm.weight | BF16 | [4096]
layers.7.attention.wq.weight -> blk.7.attn_q.weight | BF16 | [4096, 4096]
layers.7.attention.wk.weight -> blk.7.attn_k.weight | BF16 | [4096, 4096]
layers.7.attention.wv.weight -> blk.7.attn_v.weight | BF16 | [4096, 4096]
layers.7.attention.wo.weight -> blk.7.attn_output.weight | BF16 | [4096, 4096]
layers.7.feed_forward.w1.weight -> blk.7.ffn_gate.weight | BF16 | [11008, 4096]
layers.7.feed_forward.w2.weight -> blk.7.ffn_down.weight | BF16 | [4096, 11008]
layers.7.feed_forward.w3.weight -> blk.7.ffn_up.weight | BF16 | [11008, 4096]
layers.7.attention_norm.weight -> blk.7.attn_norm.weight | BF16 | [4096]
layers.7.ffn_norm.weight -> blk.7.ffn_norm.weight | BF16 | [4096]
layers.8.attention.wq.weight -> blk.8.attn_q.weight | BF16 | [4096, 4096]
layers.8.attention.wk.weight -> blk.8.attn_k.weight | BF16 | [4096, 4096]
layers.8.attention.wv.weight -> blk.8.attn_v.weight | BF16 | [4096, 4096]
layers.8.attention.wo.weight -> blk.8.attn_output.weight | BF16 | [4096, 4096]
layers.8.feed_forward.w1.weight -> blk.8.ffn_gate.weight | BF16 | [11008, 4096]
layers.8.feed_forward.w2.weight -> blk.8.ffn_down.weight | BF16 | [4096, 11008]
layers.8.feed_forward.w3.weight -> blk.8.ffn_up.weight | BF16 | [11008, 4096]
layers.8.attention_norm.weight -> blk.8.attn_norm.weight | BF16 | [4096]
layers.8.ffn_norm.weight -> blk.8.ffn_norm.weight | BF16 | [4096]
layers.9.attention.wq.weight -> blk.9.attn_q.weight | BF16 | [4096, 4096]
layers.9.attention.wk.weight -> blk.9.attn_k.weight | BF16 | [4096, 4096]
layers.9.attention.wv.weight -> blk.9.attn_v.weight | BF16 | [4096, 4096]
layers.9.attention.wo.weight -> blk.9.attn_output.weight | BF16 | [4096, 4096]
layers.9.feed_forward.w1.weight -> blk.9.ffn_gate.weight | BF16 | [11008, 4096]
layers.9.feed_forward.w2.weight -> blk.9.ffn_down.weight | BF16 | [4096, 11008]
layers.9.feed_forward.w3.weight -> blk.9.ffn_up.weight | BF16 | [11008, 4096]
layers.9.attention_norm.weight -> blk.9.attn_norm.weight | BF16 | [4096]
layers.9.ffn_norm.weight -> blk.9.ffn_norm.weight | BF16 | [4096]
layers.10.attention.wq.weight -> blk.10.attn_q.weight | BF16 | [4096, 4096]
layers.10.attention.wk.weight -> blk.10.attn_k.weight | BF16 | [4096, 4096]
layers.10.attention.wv.weight -> blk.10.attn_v.weight | BF16 | [4096, 4096]
layers.10.attention.wo.weight -> blk.10.attn_output.weight | BF16 | [4096, 4096]
layers.10.feed_forward.w1.weight -> blk.10.ffn_gate.weight | BF16 | [11008, 4096]
layers.10.feed_forward.w2.weight -> blk.10.ffn_down.weight | BF16 | [4096, 11008]
layers.10.feed_forward.w3.weight -> blk.10.ffn_up.weight | BF16 | [11008, 4096]
layers.10.attention_norm.weight -> blk.10.attn_norm.weight | BF16 | [4096]
layers.10.ffn_norm.weight -> blk.10.ffn_norm.weight | BF16 | [4096]
layers.11.attention.wq.weight -> blk.11.attn_q.weight | BF16 | [4096, 4096]
layers.11.attention.wk.weight -> blk.11.attn_k.weight | BF16 | [4096, 4096]
layers.11.attention.wv.weight -> blk.11.attn_v.weight | BF16 | [4096, 4096]
layers.11.attention.wo.weight -> blk.11.attn_output.weight | BF16 | [4096, 4096]
layers.11.feed_forward.w1.weight -> blk.11.ffn_gate.weight | BF16 | [11008, 4096]
layers.11.feed_forward.w2.weight -> blk.11.ffn_down.weight | BF16 | [4096, 11008]
layers.11.feed_forward.w3.weight -> blk.11.ffn_up.weight | BF16 | [11008, 4096]
layers.11.attention_norm.weight -> blk.11.attn_norm.weight | BF16 | [4096]
layers.11.ffn_norm.weight -> blk.11.ffn_norm.weight | BF16 | [4096]
layers.12.attention.wq.weight -> blk.12.attn_q.weight | BF16 | [4096, 4096]
layers.12.attention.wk.weight -> blk.12.attn_k.weight | BF16 | [4096, 4096]
layers.12.attention.wv.weight -> blk.12.attn_v.weight | BF16 | [4096, 4096]
layers.12.attention.wo.weight -> blk.12.attn_output.weight | BF16 | [4096, 4096]
layers.12.feed_forward.w1.weight -> blk.12.ffn_gate.weight | BF16 | [11008, 4096]
layers.12.feed_forward.w2.weight -> blk.12.ffn_down.weight | BF16 | [4096, 11008]
layers.12.feed_forward.w3.weight -> blk.12.ffn_up.weight | BF16 | [11008, 4096]
layers.12.attention_norm.weight -> blk.12.attn_norm.weight | BF16 | [4096]
layers.12.ffn_norm.weight -> blk.12.ffn_norm.weight | BF16 | [4096]
layers.13.attention.wq.weight -> blk.13.attn_q.weight | BF16 | [4096, 4096]
layers.13.attention.wk.weight -> blk.13.attn_k.weight | BF16 | [4096, 4096]
layers.13.attention.wv.weight -> blk.13.attn_v.weight | BF16 | [4096, 4096]
layers.13.attention.wo.weight -> blk.13.attn_output.weight | BF16 | [4096, 4096]
layers.13.feed_forward.w1.weight -> blk.13.ffn_gate.weight | BF16 | [11008, 4096]
layers.13.feed_forward.w2.weight -> blk.13.ffn_down.weight | BF16 | [4096, 11008]
layers.13.feed_forward.w3.weight -> blk.13.ffn_up.weight | BF16 | [11008, 4096]
layers.13.attention_norm.weight -> blk.13.attn_norm.weight | BF16 | [4096]
layers.13.ffn_norm.weight -> blk.13.ffn_norm.weight | BF16 | [4096]
layers.14.attention.wq.weight -> blk.14.attn_q.weight | BF16 | [4096, 4096]
layers.14.attention.wk.weight -> blk.14.attn_k.weight | BF16 | [4096, 4096]
layers.14.attention.wv.weight -> blk.14.attn_v.weight | BF16 | [4096, 4096]
layers.14.attention.wo.weight -> blk.14.attn_output.weight | BF16 | [4096, 4096]
layers.14.feed_forward.w1.weight -> blk.14.ffn_gate.weight | BF16 | [11008, 4096]
layers.14.feed_forward.w2.weight -> blk.14.ffn_down.weight | BF16 | [4096, 11008]
layers.14.feed_forward.w3.weight -> blk.14.ffn_up.weight | BF16 | [11008, 4096]
layers.14.attention_norm.weight -> blk.14.attn_norm.weight | BF16 | [4096]
layers.14.ffn_norm.weight -> blk.14.ffn_norm.weight | BF16 | [4096]
layers.15.attention.wq.weight -> blk.15.attn_q.weight | BF16 | [4096, 4096]
layers.15.attention.wk.weight -> blk.15.attn_k.weight | BF16 | [4096, 4096]
layers.15.attention.wv.weight -> blk.15.attn_v.weight | BF16 | [4096, 4096]
layers.15.attention.wo.weight -> blk.15.attn_output.weight | BF16 | [4096, 4096]
layers.15.feed_forward.w1.weight -> blk.15.ffn_gate.weight | BF16 | [11008, 4096]
layers.15.feed_forward.w2.weight -> blk.15.ffn_down.weight | BF16 | [4096, 11008]
layers.15.feed_forward.w3.weight -> blk.15.ffn_up.weight | BF16 | [11008, 4096]
layers.15.attention_norm.weight -> blk.15.attn_norm.weight | BF16 | [4096]
layers.15.ffn_norm.weight -> blk.15.ffn_norm.weight | BF16 | [4096]
layers.16.attention.wq.weight -> blk.16.attn_q.weight | BF16 | [4096, 4096]
layers.16.attention.wk.weight -> blk.16.attn_k.weight | BF16 | [4096, 4096]
layers.16.attention.wv.weight -> blk.16.attn_v.weight | BF16 | [4096, 4096]
layers.16.attention.wo.weight -> blk.16.attn_output.weight | BF16 | [4096, 4096]
layers.16.feed_forward.w1.weight -> blk.16.ffn_gate.weight | BF16 | [11008, 4096]
layers.16.feed_forward.w2.weight -> blk.16.ffn_down.weight | BF16 | [4096, 11008]
layers.16.feed_forward.w3.weight -> blk.16.ffn_up.weight | BF16 | [11008, 4096]
layers.16.attention_norm.weight -> blk.16.attn_norm.weight | BF16 | [4096]
layers.16.ffn_norm.weight -> blk.16.ffn_norm.weight | BF16 | [4096]
layers.17.attention.wq.weight -> blk.17.attn_q.weight | BF16 | [4096, 4096]
layers.17.attention.wk.weight -> blk.17.attn_k.weight | BF16 | [4096, 4096]
layers.17.attention.wv.weight -> blk.17.attn_v.weight | BF16 | [4096, 4096]
layers.17.attention.wo.weight -> blk.17.attn_output.weight | BF16 | [4096, 4096]
layers.17.feed_forward.w1.weight -> blk.17.ffn_gate.weight | BF16 | [11008, 4096]
layers.17.feed_forward.w2.weight -> blk.17.ffn_down.weight | BF16 | [4096, 11008]
layers.17.feed_forward.w3.weight -> blk.17.ffn_up.weight | BF16 | [11008, 4096]
layers.17.attention_norm.weight -> blk.17.attn_norm.weight | BF16 | [4096]
layers.17.ffn_norm.weight -> blk.17.ffn_norm.weight | BF16 | [4096]
layers.18.attention.wq.weight -> blk.18.attn_q.weight | BF16 | [4096, 4096]
layers.18.attention.wk.weight -> blk.18.attn_k.weight | BF16 | [4096, 4096]
layers.18.attention.wv.weight -> blk.18.attn_v.weight | BF16 | [4096, 4096]
layers.18.attention.wo.weight -> blk.18.attn_output.weight | BF16 | [4096, 4096]
layers.18.feed_forward.w1.weight -> blk.18.ffn_gate.weight | BF16 | [11008, 4096]
layers.18.feed_forward.w2.weight -> blk.18.ffn_down.weight | BF16 | [4096, 11008]
layers.18.feed_forward.w3.weight -> blk.18.ffn_up.weight | BF16 | [11008, 4096]
layers.18.attention_norm.weight -> blk.18.attn_norm.weight | BF16 | [4096]
layers.18.ffn_norm.weight -> blk.18.ffn_norm.weight | BF16 | [4096]
layers.19.attention.wq.weight -> blk.19.attn_q.weight | BF16 | [4096, 4096]
layers.19.attention.wk.weight -> blk.19.attn_k.weight | BF16 | [4096, 4096]
layers.19.attention.wv.weight -> blk.19.attn_v.weight | BF16 | [4096, 4096]
layers.19.attention.wo.weight -> blk.19.attn_output.weight | BF16 | [4096, 4096]
layers.19.feed_forward.w1.weight -> blk.19.ffn_gate.weight | BF16 | [11008, 4096]
layers.19.feed_forward.w2.weight -> blk.19.ffn_down.weight | BF16 | [4096, 11008]
layers.19.feed_forward.w3.weight -> blk.19.ffn_up.weight | BF16 | [11008, 4096]
layers.19.attention_norm.weight -> blk.19.attn_norm.weight | BF16 | [4096]
layers.19.ffn_norm.weight -> blk.19.ffn_norm.weight | BF16 | [4096]
layers.20.attention.wq.weight -> blk.20.attn_q.weight | BF16 | [4096, 4096]
layers.20.attention.wk.weight -> blk.20.attn_k.weight | BF16 | [4096, 4096]
layers.20.attention.wv.weight -> blk.20.attn_v.weight | BF16 | [4096, 4096]
layers.20.attention.wo.weight -> blk.20.attn_output.weight | BF16 | [4096, 4096]
layers.20.feed_forward.w1.weight -> blk.20.ffn_gate.weight | BF16 | [11008, 4096]
layers.20.feed_forward.w2.weight -> blk.20.ffn_down.weight | BF16 | [4096, 11008]
layers.20.feed_forward.w3.weight -> blk.20.ffn_up.weight | BF16 | [11008, 4096]
layers.20.attention_norm.weight -> blk.20.attn_norm.weight | BF16 | [4096]
layers.20.ffn_norm.weight -> blk.20.ffn_norm.weight | BF16 | [4096]
layers.21.attention.wq.weight -> blk.21.attn_q.weight | BF16 | [4096, 4096]
layers.21.attention.wk.weight -> blk.21.attn_k.weight | BF16 | [4096, 4096]
layers.21.attention.wv.weight -> blk.21.attn_v.weight | BF16 | [4096, 4096]
layers.21.attention.wo.weight -> blk.21.attn_output.weight | BF16 | [4096, 4096]
layers.21.feed_forward.w1.weight -> blk.21.ffn_gate.weight | BF16 | [11008, 4096]
layers.21.feed_forward.w2.weight -> blk.21.ffn_down.weight | BF16 | [4096, 11008]
layers.21.feed_forward.w3.weight -> blk.21.ffn_up.weight | BF16 | [11008, 4096]
layers.21.attention_norm.weight -> blk.21.attn_norm.weight | BF16 | [4096]
layers.21.ffn_norm.weight -> blk.21.ffn_norm.weight | BF16 | [4096]
layers.22.attention.wq.weight -> blk.22.attn_q.weight | BF16 | [4096, 4096]
layers.22.attention.wk.weight -> blk.22.attn_k.weight | BF16 | [4096, 4096]
layers.22.attention.wv.weight -> blk.22.attn_v.weight | BF16 | [4096, 4096]
layers.22.attention.wo.weight -> blk.22.attn_output.weight | BF16 | [4096, 4096]
layers.22.feed_forward.w1.weight -> blk.22.ffn_gate.weight | BF16 | [11008, 4096]
layers.22.feed_forward.w2.weight -> blk.22.ffn_down.weight | BF16 | [4096, 11008]
layers.22.feed_forward.w3.weight -> blk.22.ffn_up.weight | BF16 | [11008, 4096]
layers.22.attention_norm.weight -> blk.22.attn_norm.weight | BF16 | [4096]
layers.22.ffn_norm.weight -> blk.22.ffn_norm.weight | BF16 | [4096]
layers.23.attention.wq.weight -> blk.23.attn_q.weight | BF16 | [4096, 4096]
layers.23.attention.wk.weight -> blk.23.attn_k.weight | BF16 | [4096, 4096]
layers.23.attention.wv.weight -> blk.23.attn_v.weight | BF16 | [4096, 4096]
layers.23.attention.wo.weight -> blk.23.attn_output.weight | BF16 | [4096, 4096]
layers.23.feed_forward.w1.weight -> blk.23.ffn_gate.weight | BF16 | [11008, 4096]
layers.23.feed_forward.w2.weight -> blk.23.ffn_down.weight | BF16 | [4096, 11008]
layers.23.feed_forward.w3.weight -> blk.23.ffn_up.weight | BF16 | [11008, 4096]
layers.23.attention_norm.weight -> blk.23.attn_norm.weight | BF16 | [4096]
layers.23.ffn_norm.weight -> blk.23.ffn_norm.weight | BF16 | [4096]
layers.24.attention.wq.weight -> blk.24.attn_q.weight | BF16 | [4096, 4096]
layers.24.attention.wk.weight -> blk.24.attn_k.weight | BF16 | [4096, 4096]
layers.24.attention.wv.weight -> blk.24.attn_v.weight | BF16 | [4096, 4096]
layers.24.attention.wo.weight -> blk.24.attn_output.weight | BF16 | [4096, 4096]
layers.24.feed_forward.w1.weight -> blk.24.ffn_gate.weight | BF16 | [11008, 4096]
layers.24.feed_forward.w2.weight -> blk.24.ffn_down.weight | BF16 | [4096, 11008]
layers.24.feed_forward.w3.weight -> blk.24.ffn_up.weight | BF16 | [11008, 4096]
layers.24.attention_norm.weight -> blk.24.attn_norm.weight | BF16 | [4096]
layers.24.ffn_norm.weight -> blk.24.ffn_norm.weight | BF16 | [4096]
layers.25.attention.wq.weight -> blk.25.attn_q.weight | BF16 | [4096, 4096]
layers.25.attention.wk.weight -> blk.25.attn_k.weight | BF16 | [4096, 4096]
layers.25.attention.wv.weight -> blk.25.attn_v.weight | BF16 | [4096, 4096]
layers.25.attention.wo.weight -> blk.25.attn_output.weight | BF16 | [4096, 4096]
layers.25.feed_forward.w1.weight -> blk.25.ffn_gate.weight | BF16 | [11008, 4096]
layers.25.feed_forward.w2.weight -> blk.25.ffn_down.weight | BF16 | [4096, 11008]
layers.25.feed_forward.w3.weight -> blk.25.ffn_up.weight | BF16 | [11008, 4096]
layers.25.attention_norm.weight -> blk.25.attn_norm.weight | BF16 | [4096]
layers.25.ffn_norm.weight -> blk.25.ffn_norm.weight | BF16 | [4096]
layers.26.attention.wq.weight -> blk.26.attn_q.weight | BF16 | [4096, 4096]
layers.26.attention.wk.weight -> blk.26.attn_k.weight | BF16 | [4096, 4096]
layers.26.attention.wv.weight -> blk.26.attn_v.weight | BF16 | [4096, 4096]
layers.26.attention.wo.weight -> blk.26.attn_output.weight | BF16 | [4096, 4096]
layers.26.feed_forward.w1.weight -> blk.26.ffn_gate.weight | BF16 | [11008, 4096]
layers.26.feed_forward.w2.weight -> blk.26.ffn_down.weight | BF16 | [4096, 11008]
layers.26.feed_forward.w3.weight -> blk.26.ffn_up.weight | BF16 | [11008, 4096]
layers.26.attention_norm.weight -> blk.26.attn_norm.weight | BF16 | [4096]
layers.26.ffn_norm.weight -> blk.26.ffn_norm.weight | BF16 | [4096]
layers.27.attention.wq.weight -> blk.27.attn_q.weight | BF16 | [4096, 4096]
layers.27.attention.wk.weight -> blk.27.attn_k.weight | BF16 | [4096, 4096]
layers.27.attention.wv.weight -> blk.27.attn_v.weight | BF16 | [4096, 4096]
layers.27.attention.wo.weight -> blk.27.attn_output.weight | BF16 | [4096, 4096]
layers.27.feed_forward.w1.weight -> blk.27.ffn_gate.weight | BF16 | [11008, 4096]
layers.27.feed_forward.w2.weight -> blk.27.ffn_down.weight | BF16 | [4096, 11008]
layers.27.feed_forward.w3.weight -> blk.27.ffn_up.weight | BF16 | [11008, 4096]
layers.27.attention_norm.weight -> blk.27.attn_norm.weight | BF16 | [4096]
layers.27.ffn_norm.weight -> blk.27.ffn_norm.weight | BF16 | [4096]
layers.28.attention.wq.weight -> blk.28.attn_q.weight | BF16 | [4096, 4096]
layers.28.attention.wk.weight -> blk.28.attn_k.weight | BF16 | [4096, 4096]
layers.28.attention.wv.weight -> blk.28.attn_v.weight | BF16 | [4096, 4096]
layers.28.attention.wo.weight -> blk.28.attn_output.weight | BF16 | [4096, 4096]
layers.28.feed_forward.w1.weight -> blk.28.ffn_gate.weight | BF16 | [11008, 4096]
layers.28.feed_forward.w2.weight -> blk.28.ffn_down.weight | BF16 | [4096, 11008]
layers.28.feed_forward.w3.weight -> blk.28.ffn_up.weight | BF16 | [11008, 4096]
layers.28.attention_norm.weight -> blk.28.attn_norm.weight | BF16 | [4096]
layers.28.ffn_norm.weight -> blk.28.ffn_norm.weight | BF16 | [4096]
layers.29.attention.wq.weight -> blk.29.attn_q.weight | BF16 | [4096, 4096]
layers.29.attention.wk.weight -> blk.29.attn_k.weight | BF16 | [4096, 4096]
layers.29.attention.wv.weight -> blk.29.attn_v.weight | BF16 | [4096, 4096]
layers.29.attention.wo.weight -> blk.29.attn_output.weight | BF16 | [4096, 4096]
layers.29.feed_forward.w1.weight -> blk.29.ffn_gate.weight | BF16 | [11008, 4096]
layers.29.feed_forward.w2.weight -> blk.29.ffn_down.weight | BF16 | [4096, 11008]
layers.29.feed_forward.w3.weight -> blk.29.ffn_up.weight | BF16 | [11008, 4096]
layers.29.attention_norm.weight -> blk.29.attn_norm.weight | BF16 | [4096]
layers.29.ffn_norm.weight -> blk.29.ffn_norm.weight | BF16 | [4096]
layers.30.attention.wq.weight -> blk.30.attn_q.weight | BF16 | [4096, 4096]
layers.30.attention.wk.weight -> blk.30.attn_k.weight | BF16 | [4096, 4096]
layers.30.attention.wv.weight -> blk.30.attn_v.weight | BF16 | [4096, 4096]
layers.30.attention.wo.weight -> blk.30.attn_output.weight | BF16 | [4096, 4096]
layers.30.feed_forward.w1.weight -> blk.30.ffn_gate.weight | BF16 | [11008, 4096]
layers.30.feed_forward.w2.weight -> blk.30.ffn_down.weight | BF16 | [4096, 11008]
layers.30.feed_forward.w3.weight -> blk.30.ffn_up.weight | BF16 | [11008, 4096]
layers.30.attention_norm.weight -> blk.30.attn_norm.weight | BF16 | [4096]
layers.30.ffn_norm.weight -> blk.30.ffn_norm.weight | BF16 | [4096]
layers.31.attention.wq.weight -> blk.31.attn_q.weight | BF16 | [4096, 4096]
layers.31.attention.wk.weight -> blk.31.attn_k.weight | BF16 | [4096, 4096]
layers.31.attention.wv.weight -> blk.31.attn_v.weight | BF16 | [4096, 4096]
layers.31.attention.wo.weight -> blk.31.attn_output.weight | BF16 | [4096, 4096]
layers.31.feed_forward.w1.weight -> blk.31.ffn_gate.weight | BF16 | [11008, 4096]
layers.31.feed_forward.w2.weight -> blk.31.ffn_down.weight | BF16 | [4096, 11008]
layers.31.feed_forward.w3.weight -> blk.31.ffn_up.weight | BF16 | [11008, 4096]
layers.31.attention_norm.weight -> blk.31.attn_norm.weight | BF16 | [4096]
layers.31.ffn_norm.weight -> blk.31.ffn_norm.weight | BF16 | [4096]
skipping tensor rope_freqs
Writing models/Llama-7b-Chinese/ggml-model-f16.gguf, format 1
Ignoring added_tokens.json since model matches vocab size without it.
gguf: This GGUF file is for Little Endian only
gguf: Setting special token type bos to 1
gguf: Setting special token type eos to 2
gguf: Setting special token type pad to 0
gguf: Setting add_bos_token to True
gguf: Setting add_eos_token to False
[ 1/291] Writing tensor token_embd.weight | size 32000 x 4096 | type F16 | T+ 2
[ 2/291] Writing tensor output_norm.weight | size 4096 | type F32 | T+ 2
[ 3/291] Writing tensor output.weight | size 32000 x 4096 | type F16 | T+ 2
[ 4/291] Writing tensor blk.0.attn_q.weight | size 4096 x 4096 | type F16 | T+ 3
[ 5/291] Writing tensor blk.0.attn_k.weight | size 4096 x 4096 | type F16 | T+ 3
[ 6/291] Writing tensor blk.0.attn_v.weight | size 4096 x 4096 | type F16 | T+ 3
[ 7/291] Writing tensor blk.0.attn_output.weight | size 4096 x 4096 | type F16 | T+ 3
[ 8/291] Writing tensor blk.0.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 3
[ 9/291] Writing tensor blk.0.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 3
[ 10/291] Writing tensor blk.0.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 3
[ 11/291] Writing tensor blk.0.attn_norm.weight | size 4096 | type F32 | T+ 3
[ 12/291] Writing tensor blk.0.ffn_norm.weight | size 4096 | type F32 | T+ 3
[ 13/291] Writing tensor blk.1.attn_q.weight | size 4096 x 4096 | type F16 | T+ 3
[ 14/291] Writing tensor blk.1.attn_k.weight | size 4096 x 4096 | type F16 | T+ 3
[ 15/291] Writing tensor blk.1.attn_v.weight | size 4096 x 4096 | type F16 | T+ 3
[ 16/291] Writing tensor blk.1.attn_output.weight | size 4096 x 4096 | type F16 | T+ 3
[ 17/291] Writing tensor blk.1.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 3
[ 18/291] Writing tensor blk.1.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 3
[ 19/291] Writing tensor blk.1.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 3
[ 20/291] Writing tensor blk.1.attn_norm.weight | size 4096 | type F32 | T+ 3
[ 21/291] Writing tensor blk.1.ffn_norm.weight | size 4096 | type F32 | T+ 3
[ 22/291] Writing tensor blk.2.attn_q.weight | size 4096 x 4096 | type F16 | T+ 3
[ 23/291] Writing tensor blk.2.attn_k.weight | size 4096 x 4096 | type F16 | T+ 3
[ 24/291] Writing tensor blk.2.attn_v.weight | size 4096 x 4096 | type F16 | T+ 3
[ 25/291] Writing tensor blk.2.attn_output.weight | size 4096 x 4096 | type F16 | T+ 4
[ 26/291] Writing tensor blk.2.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 4
[ 27/291] Writing tensor blk.2.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 4
[ 28/291] Writing tensor blk.2.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 4
[ 29/291] Writing tensor blk.2.attn_norm.weight | size 4096 | type F32 | T+ 4
[ 30/291] Writing tensor blk.2.ffn_norm.weight | size 4096 | type F32 | T+ 4
[ 31/291] Writing tensor blk.3.attn_q.weight | size 4096 x 4096 | type F16 | T+ 4
[ 32/291] Writing tensor blk.3.attn_k.weight | size 4096 x 4096 | type F16 | T+ 4
[ 33/291] Writing tensor blk.3.attn_v.weight | size 4096 x 4096 | type F16 | T+ 5
[ 34/291] Writing tensor blk.3.attn_output.weight | size 4096 x 4096 | type F16 | T+ 5
[ 35/291] Writing tensor blk.3.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 5
[ 36/291] Writing tensor blk.3.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 5
[ 37/291] Writing tensor blk.3.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 5
[ 38/291] Writing tensor blk.3.attn_norm.weight | size 4096 | type F32 | T+ 5
[ 39/291] Writing tensor blk.3.ffn_norm.weight | size 4096 | type F32 | T+ 5
[ 40/291] Writing tensor blk.4.attn_q.weight | size 4096 x 4096 | type F16 | T+ 5
[ 41/291] Writing tensor blk.4.attn_k.weight | size 4096 x 4096 | type F16 | T+ 6
[ 42/291] Writing tensor blk.4.attn_v.weight | size 4096 x 4096 | type F16 | T+ 6
[ 43/291] Writing tensor blk.4.attn_output.weight | size 4096 x 4096 | type F16 | T+ 6
[ 44/291] Writing tensor blk.4.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 6
[ 45/291] Writing tensor blk.4.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 6
[ 46/291] Writing tensor blk.4.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 6
[ 47/291] Writing tensor blk.4.attn_norm.weight | size 4096 | type F32 | T+ 6
[ 48/291] Writing tensor blk.4.ffn_norm.weight | size 4096 | type F32 | T+ 6
[ 49/291] Writing tensor blk.5.attn_q.weight | size 4096 x 4096 | type F16 | T+ 6
[ 50/291] Writing tensor blk.5.attn_k.weight | size 4096 x 4096 | type F16 | T+ 6
[ 51/291] Writing tensor blk.5.attn_v.weight | size 4096 x 4096 | type F16 | T+ 6
[ 52/291] Writing tensor blk.5.attn_output.weight | size 4096 x 4096 | type F16 | T+ 7
[ 53/291] Writing tensor blk.5.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 7
[ 54/291] Writing tensor blk.5.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 7
[ 55/291] Writing tensor blk.5.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 7
[ 56/291] Writing tensor blk.5.attn_norm.weight | size 4096 | type F32 | T+ 7
[ 57/291] Writing tensor blk.5.ffn_norm.weight | size 4096 | type F32 | T+ 7
[ 58/291] Writing tensor blk.6.attn_q.weight | size 4096 x 4096 | type F16 | T+ 7
[ 59/291] Writing tensor blk.6.attn_k.weight | size 4096 x 4096 | type F16 | T+ 7
[ 60/291] Writing tensor blk.6.attn_v.weight | size 4096 x 4096 | type F16 | T+ 7
[ 61/291] Writing tensor blk.6.attn_output.weight | size 4096 x 4096 | type F16 | T+ 7
[ 62/291] Writing tensor blk.6.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 7
[ 63/291] Writing tensor blk.6.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 8
[ 64/291] Writing tensor blk.6.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 8
[ 65/291] Writing tensor blk.6.attn_norm.weight | size 4096 | type F32 | T+ 8
[ 66/291] Writing tensor blk.6.ffn_norm.weight | size 4096 | type F32 | T+ 8
[ 67/291] Writing tensor blk.7.attn_q.weight | size 4096 x 4096 | type F16 | T+ 8
[ 68/291] Writing tensor blk.7.attn_k.weight | size 4096 x 4096 | type F16 | T+ 8
[ 69/291] Writing tensor blk.7.attn_v.weight | size 4096 x 4096 | type F16 | T+ 8
[ 70/291] Writing tensor blk.7.attn_output.weight | size 4096 x 4096 | type F16 | T+ 8
[ 71/291] Writing tensor blk.7.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 8
[ 72/291] Writing tensor blk.7.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 9
[ 73/291] Writing tensor blk.7.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 9
[ 74/291] Writing tensor blk.7.attn_norm.weight | size 4096 | type F32 | T+ 9
[ 75/291] Writing tensor blk.7.ffn_norm.weight | size 4096 | type F32 | T+ 9
[ 76/291] Writing tensor blk.8.attn_q.weight | size 4096 x 4096 | type F16 | T+ 9
[ 77/291] Writing tensor blk.8.attn_k.weight | size 4096 x 4096 | type F16 | T+ 9
[ 78/291] Writing tensor blk.8.attn_v.weight | size 4096 x 4096 | type F16 | T+ 9
[ 79/291] Writing tensor blk.8.attn_output.weight | size 4096 x 4096 | type F16 | T+ 9
[ 80/291] Writing tensor blk.8.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 9
[ 81/291] Writing tensor blk.8.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 9
[ 82/291] Writing tensor blk.8.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 10
[ 83/291] Writing tensor blk.8.attn_norm.weight | size 4096 | type F32 | T+ 10
[ 84/291] Writing tensor blk.8.ffn_norm.weight | size 4096 | type F32 | T+ 10
[ 85/291] Writing tensor blk.9.attn_q.weight | size 4096 x 4096 | type F16 | T+ 10
[ 86/291] Writing tensor blk.9.attn_k.weight | size 4096 x 4096 | type F16 | T+ 10
[ 87/291] Writing tensor blk.9.attn_v.weight | size 4096 x 4096 | type F16 | T+ 10
[ 88/291] Writing tensor blk.9.attn_output.weight | size 4096 x 4096 | type F16 | T+ 10
[ 89/291] Writing tensor blk.9.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 10
[ 90/291] Writing tensor blk.9.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 10
[ 91/291] Writing tensor blk.9.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 10
[ 92/291] Writing tensor blk.9.attn_norm.weight | size 4096 | type F32 | T+ 10
[ 93/291] Writing tensor blk.9.ffn_norm.weight | size 4096 | type F32 | T+ 10
[ 94/291] Writing tensor blk.10.attn_q.weight | size 4096 x 4096 | type F16 | T+ 10
[ 95/291] Writing tensor blk.10.attn_k.weight | size 4096 x 4096 | type F16 | T+ 10
[ 96/291] Writing tensor blk.10.attn_v.weight | size 4096 x 4096 | type F16 | T+ 10
[ 97/291] Writing tensor blk.10.attn_output.weight | size 4096 x 4096 | type F16 | T+ 10
[ 98/291] Writing tensor blk.10.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 10
[ 99/291] Writing tensor blk.10.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 11
[100/291] Writing tensor blk.10.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 11
[101/291] Writing tensor blk.10.attn_norm.weight | size 4096 | type F32 | T+ 11
[102/291] Writing tensor blk.10.ffn_norm.weight | size 4096 | type F32 | T+ 11
[103/291] Writing tensor blk.11.attn_q.weight | size 4096 x 4096 | type F16 | T+ 11
[104/291] Writing tensor blk.11.attn_k.weight | size 4096 x 4096 | type F16 | T+ 11
[105/291] Writing tensor blk.11.attn_v.weight | size 4096 x 4096 | type F16 | T+ 11
[106/291] Writing tensor blk.11.attn_output.weight | size 4096 x 4096 | type F16 | T+ 11
[107/291] Writing tensor blk.11.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 11
[108/291] Writing tensor blk.11.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 12
[109/291] Writing tensor blk.11.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 12
[110/291] Writing tensor blk.11.attn_norm.weight | size 4096 | type F32 | T+ 12
[111/291] Writing tensor blk.11.ffn_norm.weight | size 4096 | type F32 | T+ 12
[112/291] Writing tensor blk.12.attn_q.weight | size 4096 x 4096 | type F16 | T+ 12
[113/291] Writing tensor blk.12.attn_k.weight | size 4096 x 4096 | type F16 | T+ 12
[114/291] Writing tensor blk.12.attn_v.weight | size 4096 x 4096 | type F16 | T+ 12
[115/291] Writing tensor blk.12.attn_output.weight | size 4096 x 4096 | type F16 | T+ 12
[116/291] Writing tensor blk.12.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 12
[117/291] Writing tensor blk.12.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 12
[118/291] Writing tensor blk.12.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 13
[119/291] Writing tensor blk.12.attn_norm.weight | size 4096 | type F32 | T+ 13
[120/291] Writing tensor blk.12.ffn_norm.weight | size 4096 | type F32 | T+ 13
[121/291] Writing tensor blk.13.attn_q.weight | size 4096 x 4096 | type F16 | T+ 13
[122/291] Writing tensor blk.13.attn_k.weight | size 4096 x 4096 | type F16 | T+ 13
[123/291] Writing tensor blk.13.attn_v.weight | size 4096 x 4096 | type F16 | T+ 13
[124/291] Writing tensor blk.13.attn_output.weight | size 4096 x 4096 | type F16 | T+ 13
[125/291] Writing tensor blk.13.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 13
[126/291] Writing tensor blk.13.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 13
[127/291] Writing tensor blk.13.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 13
[128/291] Writing tensor blk.13.attn_norm.weight | size 4096 | type F32 | T+ 13
[129/291] Writing tensor blk.13.ffn_norm.weight | size 4096 | type F32 | T+ 13
[130/291] Writing tensor blk.14.attn_q.weight | size 4096 x 4096 | type F16 | T+ 13
[131/291] Writing tensor blk.14.attn_k.weight | size 4096 x 4096 | type F16 | T+ 13
[132/291] Writing tensor blk.14.attn_v.weight | size 4096 x 4096 | type F16 | T+ 13
[133/291] Writing tensor blk.14.attn_output.weight | size 4096 x 4096 | type F16 | T+ 13
[134/291] Writing tensor blk.14.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 13
[135/291] Writing tensor blk.14.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 13
[136/291] Writing tensor blk.14.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 14
[137/291] Writing tensor blk.14.attn_norm.weight | size 4096 | type F32 | T+ 14
[138/291] Writing tensor blk.14.ffn_norm.weight | size 4096 | type F32 | T+ 14
[139/291] Writing tensor blk.15.attn_q.weight | size 4096 x 4096 | type F16 | T+ 14
[140/291] Writing tensor blk.15.attn_k.weight | size 4096 x 4096 | type F16 | T+ 14
[141/291] Writing tensor blk.15.attn_v.weight | size 4096 x 4096 | type F16 | T+ 14
[142/291] Writing tensor blk.15.attn_output.weight | size 4096 x 4096 | type F16 | T+ 14
[143/291] Writing tensor blk.15.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 14
[144/291] Writing tensor blk.15.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 14
[145/291] Writing tensor blk.15.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 14
[146/291] Writing tensor blk.15.attn_norm.weight | size 4096 | type F32 | T+ 14
[147/291] Writing tensor blk.15.ffn_norm.weight | size 4096 | type F32 | T+ 14
[148/291] Writing tensor blk.16.attn_q.weight | size 4096 x 4096 | type F16 | T+ 14
[149/291] Writing tensor blk.16.attn_k.weight | size 4096 x 4096 | type F16 | T+ 14
[150/291] Writing tensor blk.16.attn_v.weight | size 4096 x 4096 | type F16 | T+ 14
[151/291] Writing tensor blk.16.attn_output.weight | size 4096 x 4096 | type F16 | T+ 14
[152/291] Writing tensor blk.16.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 14
[153/291] Writing tensor blk.16.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 14
[154/291] Writing tensor blk.16.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 15
[155/291] Writing tensor blk.16.attn_norm.weight | size 4096 | type F32 | T+ 15
[156/291] Writing tensor blk.16.ffn_norm.weight | size 4096 | type F32 | T+ 15
[157/291] Writing tensor blk.17.attn_q.weight | size 4096 x 4096 | type F16 | T+ 15
[158/291] Writing tensor blk.17.attn_k.weight | size 4096 x 4096 | type F16 | T+ 15
[159/291] Writing tensor blk.17.attn_v.weight | size 4096 x 4096 | type F16 | T+ 15
[160/291] Writing tensor blk.17.attn_output.weight | size 4096 x 4096 | type F16 | T+ 15
[161/291] Writing tensor blk.17.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 15
[162/291] Writing tensor blk.17.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 15
[163/291] Writing tensor blk.17.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 15
[164/291] Writing tensor blk.17.attn_norm.weight | size 4096 | type F32 | T+ 15
[165/291] Writing tensor blk.17.ffn_norm.weight | size 4096 | type F32 | T+ 15
[166/291] Writing tensor blk.18.attn_q.weight | size 4096 x 4096 | type F16 | T+ 15
[167/291] Writing tensor blk.18.attn_k.weight | size 4096 x 4096 | type F16 | T+ 15
[168/291] Writing tensor blk.18.attn_v.weight | size 4096 x 4096 | type F16 | T+ 15
[169/291] Writing tensor blk.18.attn_output.weight | size 4096 x 4096 | type F16 | T+ 15
[170/291] Writing tensor blk.18.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 15
[171/291] Writing tensor blk.18.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 16
[172/291] Writing tensor blk.18.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 16
[173/291] Writing tensor blk.18.attn_norm.weight | size 4096 | type F32 | T+ 16
[174/291] Writing tensor blk.18.ffn_norm.weight | size 4096 | type F32 | T+ 16
[175/291] Writing tensor blk.19.attn_q.weight | size 4096 x 4096 | type F16 | T+ 16
[176/291] Writing tensor blk.19.attn_k.weight | size 4096 x 4096 | type F16 | T+ 16
[177/291] Writing tensor blk.19.attn_v.weight | size 4096 x 4096 | type F16 | T+ 16
[178/291] Writing tensor blk.19.attn_output.weight | size 4096 x 4096 | type F16 | T+ 16
[179/291] Writing tensor blk.19.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 16
[180/291] Writing tensor blk.19.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 16
[181/291] Writing tensor blk.19.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 16
[182/291] Writing tensor blk.19.attn_norm.weight | size 4096 | type F32 | T+ 16
[183/291] Writing tensor blk.19.ffn_norm.weight | size 4096 | type F32 | T+ 16
[184/291] Writing tensor blk.20.attn_q.weight | size 4096 x 4096 | type F16 | T+ 16
[185/291] Writing tensor blk.20.attn_k.weight | size 4096 x 4096 | type F16 | T+ 16
[186/291] Writing tensor blk.20.attn_v.weight | size 4096 x 4096 | type F16 | T+ 16
[187/291] Writing tensor blk.20.attn_output.weight | size 4096 x 4096 | type F16 | T+ 16
[188/291] Writing tensor blk.20.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 16
[189/291] Writing tensor blk.20.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 17
[190/291] Writing tensor blk.20.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 17
[191/291] Writing tensor blk.20.attn_norm.weight | size 4096 | type F32 | T+ 17
[192/291] Writing tensor blk.20.ffn_norm.weight | size 4096 | type F32 | T+ 17
[193/291] Writing tensor blk.21.attn_q.weight | size 4096 x 4096 | type F16 | T+ 17
[194/291] Writing tensor blk.21.attn_k.weight | size 4096 x 4096 | type F16 | T+ 17
[195/291] Writing tensor blk.21.attn_v.weight | size 4096 x 4096 | type F16 | T+ 17
[196/291] Writing tensor blk.21.attn_output.weight | size 4096 x 4096 | type F16 | T+ 17
[197/291] Writing tensor blk.21.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 17
[198/291] Writing tensor blk.21.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 17
[199/291] Writing tensor blk.21.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 17
[200/291] Writing tensor blk.21.attn_norm.weight | size 4096 | type F32 | T+ 17
[201/291] Writing tensor blk.21.ffn_norm.weight | size 4096 | type F32 | T+ 17
[202/291] Writing tensor blk.22.attn_q.weight | size 4096 x 4096 | type F16 | T+ 17
[203/291] Writing tensor blk.22.attn_k.weight | size 4096 x 4096 | type F16 | T+ 17
[204/291] Writing tensor blk.22.attn_v.weight | size 4096 x 4096 | type F16 | T+ 17
[205/291] Writing tensor blk.22.attn_output.weight | size 4096 x 4096 | type F16 | T+ 17
[206/291] Writing tensor blk.22.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 17
[207/291] Writing tensor blk.22.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 17
[208/291] Writing tensor blk.22.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 18
[209/291] Writing tensor blk.22.attn_norm.weight | size 4096 | type F32 | T+ 18
[210/291] Writing tensor blk.22.ffn_norm.weight | size 4096 | type F32 | T+ 18
[211/291] Writing tensor blk.23.attn_q.weight | size 4096 x 4096 | type F16 | T+ 18
[212/291] Writing tensor blk.23.attn_k.weight | size 4096 x 4096 | type F16 | T+ 18
[213/291] Writing tensor blk.23.attn_v.weight | size 4096 x 4096 | type F16 | T+ 18
[214/291] Writing tensor blk.23.attn_output.weight | size 4096 x 4096 | type F16 | T+ 18
[215/291] Writing tensor blk.23.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 18
[216/291] Writing tensor blk.23.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 18
[217/291] Writing tensor blk.23.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 18
[218/291] Writing tensor blk.23.attn_norm.weight | size 4096 | type F32 | T+ 18
[219/291] Writing tensor blk.23.ffn_norm.weight | size 4096 | type F32 | T+ 18
[220/291] Writing tensor blk.24.attn_q.weight | size 4096 x 4096 | type F16 | T+ 18
[221/291] Writing tensor blk.24.attn_k.weight | size 4096 x 4096 | type F16 | T+ 18
[222/291] Writing tensor blk.24.attn_v.weight | size 4096 x 4096 | type F16 | T+ 18
[223/291] Writing tensor blk.24.attn_output.weight | size 4096 x 4096 | type F16 | T+ 18
[224/291] Writing tensor blk.24.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 18
[225/291] Writing tensor blk.24.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 18
[226/291] Writing tensor blk.24.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 18
[227/291] Writing tensor blk.24.attn_norm.weight | size 4096 | type F32 | T+ 18
[228/291] Writing tensor blk.24.ffn_norm.weight | size 4096 | type F32 | T+ 18
[229/291] Writing tensor blk.25.attn_q.weight | size 4096 x 4096 | type F16 | T+ 18
[230/291] Writing tensor blk.25.attn_k.weight | size 4096 x 4096 | type F16 | T+ 18
[231/291] Writing tensor blk.25.attn_v.weight | size 4096 x 4096 | type F16 | T+ 18
[232/291] Writing tensor blk.25.attn_output.weight | size 4096 x 4096 | type F16 | T+ 18
[233/291] Writing tensor blk.25.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 19
[234/291] Writing tensor blk.25.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 19
[235/291] Writing tensor blk.25.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 19
[236/291] Writing tensor blk.25.attn_norm.weight | size 4096 | type F32 | T+ 19
[237/291] Writing tensor blk.25.ffn_norm.weight | size 4096 | type F32 | T+ 19
[238/291] Writing tensor blk.26.attn_q.weight | size 4096 x 4096 | type F16 | T+ 19
[239/291] Writing tensor blk.26.attn_k.weight | size 4096 x 4096 | type F16 | T+ 19
[240/291] Writing tensor blk.26.attn_v.weight | size 4096 x 4096 | type F16 | T+ 19
[241/291] Writing tensor blk.26.attn_output.weight | size 4096 x 4096 | type F16 | T+ 19
[242/291] Writing tensor blk.26.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 19
[243/291] Writing tensor blk.26.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 19
[244/291] Writing tensor blk.26.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 19
[245/291] Writing tensor blk.26.attn_norm.weight | size 4096 | type F32 | T+ 19
[246/291] Writing tensor blk.26.ffn_norm.weight | size 4096 | type F32 | T+ 19
[247/291] Writing tensor blk.27.attn_q.weight | size 4096 x 4096 | type F16 | T+ 19
[248/291] Writing tensor blk.27.attn_k.weight | size 4096 x 4096 | type F16 | T+ 19
[249/291] Writing tensor blk.27.attn_v.weight | size 4096 x 4096 | type F16 | T+ 19
[250/291] Writing tensor blk.27.attn_output.weight | size 4096 x 4096 | type F16 | T+ 19
[251/291] Writing tensor blk.27.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 19
[252/291] Writing tensor blk.27.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 20
[253/291] Writing tensor blk.27.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 20
[254/291] Writing tensor blk.27.attn_norm.weight | size 4096 | type F32 | T+ 20
[255/291] Writing tensor blk.27.ffn_norm.weight | size 4096 | type F32 | T+ 20
[256/291] Writing tensor blk.28.attn_q.weight | size 4096 x 4096 | type F16 | T+ 20
[257/291] Writing tensor blk.28.attn_k.weight | size 4096 x 4096 | type F16 | T+ 20
[258/291] Writing tensor blk.28.attn_v.weight | size 4096 x 4096 | type F16 | T+ 20
[259/291] Writing tensor blk.28.attn_output.weight | size 4096 x 4096 | type F16 | T+ 20
[260/291] Writing tensor blk.28.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 20
[261/291] Writing tensor blk.28.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 20
[262/291] Writing tensor blk.28.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 20
[263/291] Writing tensor blk.28.attn_norm.weight | size 4096 | type F32 | T+ 20
[264/291] Writing tensor blk.28.ffn_norm.weight | size 4096 | type F32 | T+ 20
[265/291] Writing tensor blk.29.attn_q.weight | size 4096 x 4096 | type F16 | T+ 20
[266/291] Writing tensor blk.29.attn_k.weight | size 4096 x 4096 | type F16 | T+ 20
[267/291] Writing tensor blk.29.attn_v.weight | size 4096 x 4096 | type F16 | T+ 20
[268/291] Writing tensor blk.29.attn_output.weight | size 4096 x 4096 | type F16 | T+ 20
[269/291] Writing tensor blk.29.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 20
[270/291] Writing tensor blk.29.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 20
[271/291] Writing tensor blk.29.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 21
[272/291] Writing tensor blk.29.attn_norm.weight | size 4096 | type F32 | T+ 21
[273/291] Writing tensor blk.29.ffn_norm.weight | size 4096 | type F32 | T+ 21
[274/291] Writing tensor blk.30.attn_q.weight | size 4096 x 4096 | type F16 | T+ 21
[275/291] Writing tensor blk.30.attn_k.weight | size 4096 x 4096 | type F16 | T+ 21
[276/291] Writing tensor blk.30.attn_v.weight | size 4096 x 4096 | type F16 | T+ 21
[277/291] Writing tensor blk.30.attn_output.weight | size 4096 x 4096 | type F16 | T+ 21
[278/291] Writing tensor blk.30.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 21
[279/291] Writing tensor blk.30.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 21
[280/291] Writing tensor blk.30.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 21
[281/291] Writing tensor blk.30.attn_norm.weight | size 4096 | type F32 | T+ 21
[282/291] Writing tensor blk.30.ffn_norm.weight | size 4096 | type F32 | T+ 21
[283/291] Writing tensor blk.31.attn_q.weight | size 4096 x 4096 | type F16 | T+ 21
[284/291] Writing tensor blk.31.attn_k.weight | size 4096 x 4096 | type F16 | T+ 21
[285/291] Writing tensor blk.31.attn_v.weight | size 4096 x 4096 | type F16 | T+ 21
[286/291] Writing tensor blk.31.attn_output.weight | size 4096 x 4096 | type F16 | T+ 21
[287/291] Writing tensor blk.31.ffn_gate.weight | size 11008 x 4096 | type F16 | T+ 21
[288/291] Writing tensor blk.31.ffn_down.weight | size 4096 x 11008 | type F16 | T+ 21
[289/291] Writing tensor blk.31.ffn_up.weight | size 11008 x 4096 | type F16 | T+ 21
[290/291] Writing tensor blk.31.attn_norm.weight | size 4096 | type F32 | T+ 21
[291/291] Writing tensor blk.31.ffn_norm.weight | size 4096 | type F32 | T+ 21
Wrote models/Llama-7b-Chinese/ggml-model-f16.gguf
(Llama-7b-Chinese) :~/newmodels/llama.cpp$
量化操作
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ ./quantize ./models/Llama-7b-Chinese/ggml-model-f16.gguf ./models/Llama-7b-Chinese/ggml-model-q4_0.gguf q4_0
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3080 Ti Laptop GPU, compute capability 8.6, VMM: yes
main: build = 2038 (7013716)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: quantizing './models/Llama-7b-Chinese/ggml-model-f16.gguf' to './models/Llama-7b-Chinese/ggml-model-q4_0.gguf' as Q4_0
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from ./models/Llama-7b-Chinese/ggml-model-f16.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = models
llama_model_loader: - kv 2: llama.context_length u32 = 2048
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 1
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 18: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 19: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 226 tensors
llama_model_quantize_internal: meta size = 741120 bytes
[ 1/ 291] token_embd.weight - [ 4096, 32000, 1, 1], type = f16, quantizing to q4_0 .. size = 250.00 MiB -> 70.31 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 2/ 291] output_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 3/ 291] output.weight - [ 4096, 32000, 1, 1], type = f16, quantizing to q6_K .. size = 250.00 MiB -> 102.54 MiB
[ 4/ 291] blk.0.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.034 0.008 0.012 0.019 0.031 0.050 0.084 0.149 0.256 0.150 0.084 0.051 0.031 0.019 0.012 0.010
[ 5/ 291] blk.0.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.034 0.008 0.013 0.021 0.033 0.054 0.089 0.150 0.226 0.151 0.089 0.054 0.033 0.021 0.013 0.011
[ 6/ 291] blk.0.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.024 0.036 0.053 0.074 0.096 0.117 0.129 0.117 0.096 0.074 0.053 0.036 0.024 0.020
[ 7/ 291] blk.0.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.035 0.011 0.017 0.028 0.044 0.068 0.100 0.135 0.155 0.135 0.100 0.068 0.044 0.028 0.017 0.014
[ 8/ 291] blk.0.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 9/ 291] blk.0.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 10/ 291] blk.0.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 11/ 291] blk.0.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 12/ 291] blk.0.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 13/ 291] blk.1.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.013 0.022 0.034 0.052 0.074 0.098 0.121 0.132 0.121 0.098 0.074 0.052 0.034 0.022 0.018
[ 14/ 291] blk.1.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.013 0.022 0.034 0.051 0.074 0.099 0.121 0.132 0.121 0.099 0.074 0.051 0.034 0.022 0.018
[ 15/ 291] blk.1.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.014 0.023 0.035 0.052 0.073 0.097 0.119 0.130 0.119 0.097 0.074 0.052 0.035 0.023 0.019
[ 16/ 291] blk.1.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.035 0.012 0.020 0.031 0.047 0.070 0.098 0.129 0.146 0.129 0.099 0.070 0.047 0.031 0.020 0.016
[ 17/ 291] blk.1.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 18/ 291] blk.1.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 19/ 291] blk.1.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 20/ 291] blk.1.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 21/ 291] blk.1.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 22/ 291] blk.2.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.024 0.038 0.055 0.076 0.096 0.114 0.122 0.114 0.097 0.076 0.055 0.038 0.024 0.020
[ 23/ 291] blk.2.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.024 0.037 0.055 0.075 0.097 0.115 0.124 0.115 0.097 0.075 0.055 0.037 0.024 0.020
[ 24/ 291] blk.2.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.120 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 25/ 291] blk.2.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 26/ 291] blk.2.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 27/ 291] blk.2.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 28/ 291] blk.2.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 29/ 291] blk.2.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 30/ 291] blk.2.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 31/ 291] blk.3.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.113 0.120 0.113 0.097 0.076 0.056 0.038 0.025 0.020
[ 32/ 291] blk.3.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.113 0.120 0.113 0.096 0.076 0.056 0.038 0.025 0.020
[ 33/ 291] blk.3.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 34/ 291] blk.3.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 35/ 291] blk.3.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 36/ 291] blk.3.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 37/ 291] blk.3.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 38/ 291] blk.3.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 39/ 291] blk.3.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 40/ 291] blk.4.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.038 0.025 0.021
[ 41/ 291] blk.4.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.113 0.120 0.113 0.096 0.076 0.056 0.038 0.025 0.020
[ 42/ 291] blk.4.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 43/ 291] blk.4.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 44/ 291] blk.4.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 45/ 291] blk.4.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 46/ 291] blk.4.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 47/ 291] blk.4.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 48/ 291] blk.4.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 49/ 291] blk.5.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.112 0.119 0.112 0.097 0.076 0.056 0.038 0.025 0.021
[ 50/ 291] blk.5.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.113 0.119 0.113 0.096 0.076 0.056 0.038 0.025 0.020
[ 51/ 291] blk.5.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 52/ 291] blk.5.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 53/ 291] blk.5.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 54/ 291] blk.5.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 55/ 291] blk.5.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 56/ 291] blk.5.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 57/ 291] blk.5.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 58/ 291] blk.6.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 59/ 291] blk.6.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 60/ 291] blk.6.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 61/ 291] blk.6.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.097 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 62/ 291] blk.6.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 63/ 291] blk.6.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 64/ 291] blk.6.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 65/ 291] blk.6.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 66/ 291] blk.6.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 67/ 291] blk.7.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.076 0.056 0.039 0.025 0.021
[ 68/ 291] blk.7.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 69/ 291] blk.7.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 70/ 291] blk.7.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.056 0.039 0.025 0.021
[ 71/ 291] blk.7.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 72/ 291] blk.7.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 73/ 291] blk.7.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 74/ 291] blk.7.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 75/ 291] blk.7.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 76/ 291] blk.8.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.097 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 77/ 291] blk.8.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 78/ 291] blk.8.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 79/ 291] blk.8.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 80/ 291] blk.8.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 81/ 291] blk.8.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 82/ 291] blk.8.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 83/ 291] blk.8.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 84/ 291] blk.8.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 85/ 291] blk.9.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 86/ 291] blk.9.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 87/ 291] blk.9.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 88/ 291] blk.9.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 89/ 291] blk.9.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 90/ 291] blk.9.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 91/ 291] blk.9.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 92/ 291] blk.9.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 93/ 291] blk.9.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 94/ 291] blk.10.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 95/ 291] blk.10.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 96/ 291] blk.10.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 97/ 291] blk.10.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.026 0.021
[ 98/ 291] blk.10.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 99/ 291] blk.10.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 100/ 291] blk.10.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 101/ 291] blk.10.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 102/ 291] blk.10.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 103/ 291] blk.11.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 104/ 291] blk.11.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 105/ 291] blk.11.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.038 0.025 0.021
[ 106/ 291] blk.11.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 107/ 291] blk.11.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 108/ 291] blk.11.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 109/ 291] blk.11.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 110/ 291] blk.11.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 111/ 291] blk.11.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 112/ 291] blk.12.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.112 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 113/ 291] blk.12.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 114/ 291] blk.12.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 115/ 291] blk.12.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 116/ 291] blk.12.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 117/ 291] blk.12.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 118/ 291] blk.12.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 119/ 291] blk.12.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 120/ 291] blk.12.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 121/ 291] blk.13.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 122/ 291] blk.13.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 123/ 291] blk.13.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.112 0.118 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 124/ 291] blk.13.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 125/ 291] blk.13.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 126/ 291] blk.13.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 127/ 291] blk.13.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 128/ 291] blk.13.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 129/ 291] blk.13.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 130/ 291] blk.14.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 131/ 291] blk.14.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 132/ 291] blk.14.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 133/ 291] blk.14.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 134/ 291] blk.14.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 135/ 291] blk.14.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 136/ 291] blk.14.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 137/ 291] blk.14.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 138/ 291] blk.14.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 139/ 291] blk.15.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 140/ 291] blk.15.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 141/ 291] blk.15.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 142/ 291] blk.15.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 143/ 291] blk.15.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 144/ 291] blk.15.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 145/ 291] blk.15.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 146/ 291] blk.15.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 147/ 291] blk.15.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 148/ 291] blk.16.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 149/ 291] blk.16.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 150/ 291] blk.16.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.112 0.118 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 151/ 291] blk.16.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.026 0.021
[ 152/ 291] blk.16.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 153/ 291] blk.16.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 154/ 291] blk.16.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 155/ 291] blk.16.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 156/ 291] blk.16.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 157/ 291] blk.17.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 158/ 291] blk.17.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 159/ 291] blk.17.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.118 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 160/ 291] blk.17.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 161/ 291] blk.17.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 162/ 291] blk.17.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.056 0.039 0.025 0.021
[ 163/ 291] blk.17.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 164/ 291] blk.17.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 165/ 291] blk.17.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 166/ 291] blk.18.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 167/ 291] blk.18.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 168/ 291] blk.18.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 169/ 291] blk.18.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 170/ 291] blk.18.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 171/ 291] blk.18.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.056 0.039 0.025 0.021
[ 172/ 291] blk.18.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 173/ 291] blk.18.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 174/ 291] blk.18.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 175/ 291] blk.19.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 176/ 291] blk.19.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 177/ 291] blk.19.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.111 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 178/ 291] blk.19.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 179/ 291] blk.19.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 180/ 291] blk.19.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 181/ 291] blk.19.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 182/ 291] blk.19.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 183/ 291] blk.19.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 184/ 291] blk.20.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.056 0.039 0.025 0.021
[ 185/ 291] blk.20.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 186/ 291] blk.20.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.076 0.096 0.112 0.118 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 187/ 291] blk.20.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.097 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 188/ 291] blk.20.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 189/ 291] blk.20.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 190/ 291] blk.20.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 191/ 291] blk.20.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 192/ 291] blk.20.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 193/ 291] blk.21.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 194/ 291] blk.21.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 195/ 291] blk.21.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 196/ 291] blk.21.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 197/ 291] blk.21.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 198/ 291] blk.21.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 199/ 291] blk.21.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 200/ 291] blk.21.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 201/ 291] blk.21.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 202/ 291] blk.22.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 203/ 291] blk.22.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.076 0.056 0.039 0.025 0.021
[ 204/ 291] blk.22.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 205/ 291] blk.22.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 206/ 291] blk.22.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 207/ 291] blk.22.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 208/ 291] blk.22.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 209/ 291] blk.22.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 210/ 291] blk.22.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 211/ 291] blk.23.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.111 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 212/ 291] blk.23.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 213/ 291] blk.23.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 214/ 291] blk.23.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.026 0.021
[ 215/ 291] blk.23.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 216/ 291] blk.23.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 217/ 291] blk.23.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 218/ 291] blk.23.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 219/ 291] blk.23.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 220/ 291] blk.24.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 221/ 291] blk.24.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.097 0.112 0.118 0.112 0.097 0.076 0.056 0.039 0.025 0.021
[ 222/ 291] blk.24.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 223/ 291] blk.24.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.026 0.021
[ 224/ 291] blk.24.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 225/ 291] blk.24.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 226/ 291] blk.24.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 227/ 291] blk.24.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 228/ 291] blk.24.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 229/ 291] blk.25.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 230/ 291] blk.25.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 231/ 291] blk.25.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 232/ 291] blk.25.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 233/ 291] blk.25.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 234/ 291] blk.25.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 235/ 291] blk.25.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 236/ 291] blk.25.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 237/ 291] blk.25.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 238/ 291] blk.26.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 239/ 291] blk.26.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 240/ 291] blk.26.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 241/ 291] blk.26.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 242/ 291] blk.26.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 243/ 291] blk.26.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 244/ 291] blk.26.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 245/ 291] blk.26.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 246/ 291] blk.26.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 247/ 291] blk.27.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 248/ 291] blk.27.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.112 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 249/ 291] blk.27.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 250/ 291] blk.27.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 251/ 291] blk.27.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 252/ 291] blk.27.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 253/ 291] blk.27.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 254/ 291] blk.27.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 255/ 291] blk.27.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 256/ 291] blk.28.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.111 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 257/ 291] blk.28.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 258/ 291] blk.28.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 259/ 291] blk.28.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 260/ 291] blk.28.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 261/ 291] blk.28.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 262/ 291] blk.28.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 263/ 291] blk.28.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 264/ 291] blk.28.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 265/ 291] blk.29.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 266/ 291] blk.29.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 267/ 291] blk.29.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 268/ 291] blk.29.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 269/ 291] blk.29.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 270/ 291] blk.29.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.112 0.118 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 271/ 291] blk.29.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 272/ 291] blk.29.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 273/ 291] blk.29.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 274/ 291] blk.30.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.096 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 275/ 291] blk.30.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.039 0.056 0.077 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
[ 276/ 291] blk.30.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.118 0.111 0.096 0.077 0.056 0.039 0.025 0.021
[ 277/ 291] blk.30.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.037 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.116 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 278/ 291] blk.30.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 279/ 291] blk.30.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.024 0.038 0.055 0.076 0.097 0.114 0.120 0.114 0.097 0.076 0.055 0.038 0.024 0.020
[ 280/ 291] blk.30.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.096 0.111 0.117 0.111 0.096 0.077 0.057 0.039 0.025 0.021
[ 281/ 291] blk.30.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 282/ 291] blk.30.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 283/ 291] blk.31.attn_q.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.112 0.119 0.112 0.097 0.077 0.056 0.038 0.025 0.021
[ 284/ 291] blk.31.attn_k.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.112 0.118 0.112 0.097 0.076 0.056 0.038 0.025 0.021
[ 285/ 291] blk.31.attn_v.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.015 0.025 0.038 0.056 0.076 0.097 0.112 0.119 0.112 0.096 0.076 0.056 0.039 0.025 0.021
[ 286/ 291] blk.31.attn_output.weight - [ 4096, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 32.00 MiB -> 9.00 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.096 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 287/ 291] blk.31.ffn_gate.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.057 0.077 0.097 0.111 0.117 0.111 0.097 0.077 0.057 0.039 0.025 0.021
[ 288/ 291] blk.31.ffn_down.weight - [11008, 4096, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.015 0.023 0.036 0.054 0.075 0.098 0.116 0.124 0.116 0.098 0.075 0.054 0.036 0.023 0.019
[ 289/ 291] blk.31.ffn_up.weight - [ 4096, 11008, 1, 1], type = f16, quantizing to q4_0 .. size = 86.00 MiB -> 24.19 MiB | hist: 0.036 0.016 0.025 0.039 0.056 0.077 0.097 0.112 0.117 0.112 0.097 0.077 0.056 0.039 0.025 0.021
[ 290/ 291] blk.31.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
[ 291/ 291] blk.31.ffn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MB
llama_model_quantize_internal: model size = 12853.02 MB
llama_model_quantize_internal: quant size = 3647.87 MB
llama_model_quantize_internal: hist: 0.036 0.015 0.025 0.039 0.056 0.076 0.096 0.112 0.118 0.112 0.096 0.077 0.056 0.039 0.025 0.021
main: quantize time = 4430.95 ms
main: total time = 4430.95 ms
执行命令（ggml-model-f16.gguf）
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ ./main -m ./models/Llama-7b-Chinese/ggml-model-f16.gguf -n 512 --n-gpu-layers 100 --prompt "我给大家介绍一下中国"
Log start
main: build = 2038 (7013716)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1713953724
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3080 Ti Laptop GPU, compute capability 8.6, VMM: yes
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from ./models/Llama-7b-Chinese/ggml-model-f16.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = models
llama_model_loader: - kv 2: llama.context_length u32 = 2048
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 1
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 18: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 19: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 226 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 2048
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 11008
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 2048
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = F16
llm_load_print_meta: model params = 6.74 B
llm_load_print_meta: model size = 12.55 GiB (16.00 BPW)
llm_load_print_meta: general.name = models
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.22 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors: CPU buffer size = 250.00 MiB
llm_load_tensors: CUDA0 buffer size = 12603.02 MiB
...................................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 256.00 MiB
llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
llama_new_context_with_model: CUDA_Host input buffer size = 9.01 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 77.55 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 8.80 MiB
llama_new_context_with_model: graph splits (measure): 3
system_info: n_threads = 10 / 20 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
sampling:
repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp
generate: n_ctx = 512, n_batch = 512, n_predict = 512, n_keep = 0
我给大家介绍一下中国的奢侈品，让大家更加了解中国的文化吧。
- 静电洗头器（一种高科技尽管相对较新的设备）
- 自动牌纸机（手抓是最古老的方式）
- 梦译术士（即将变成一种科技，但目前还有很多人在这上市风险高）
- 纸牌（现在的童子军也不是只用石头了，因为我们并不是满洲里的一个文化，所以学习方式和思想都不同）
- 钢琴（中国人最喜欢弹箱子，所以我们在家中经常会有这种东西，当然如果你去中国见过老人仍是使用打铃招待的时候，那不可能是钢琴）
- 牛皮（一些高档的餐馆会给客人赠送牛皮来进行卫生保健，或者说我们现在还是喜欢看假面貌而不是真面目）
- 手表（这里要特意注明：中国人喜欢装饰自己的手上的东西，所以我们绝对不会只买一只手表）
- 美甲、化妆品、肤脓（中国古代人的时候拿木头去除蛀牙或者切开颊口来休息，如果你在北京一旁看到了老人们都是这样的）
- 手机、电视（中国有些地
llama_print_timings: load time = 2104.31 ms
llama_print_timings: sample time = 88.61 ms / 512 runs ( 0.17 ms per token, 5777.93 tokens per second)
llama_print_timings: prompt eval time = 44.33 ms / 14 tokens ( 3.17 ms per token, 315.80 tokens per second)
llama_print_timings: eval time = 22674.35 ms / 511 runs ( 44.37 ms per token, 22.54 tokens per second)
llama_print_timings: total time = 22960.52 ms / 525 tokens
Log end
(Llama-7b-Chinese) :~/newmodels/llama.cpp$
nvidia-smi命令实时查看指定GPU使用情况
watch -n 1 nvidia-smi # 1代表每隔1秒刷新一次GPU使用情况
NVIDIA-SMI 550.76.01 #GRID版本
Driver Version: 552.22 #驱动版本
CUDA Version: 12.4 #CUDA最高支持的版本
GPU：本机中的GPU编号，从0开始，本机只有一块GPU
Fan：风扇转速（0%-100%），N/A表示没有风扇
Name：GPU名字/类型，NVIDIA GeForce RTX 3080TI
Temp：GPU温度（GPU温度过高会导致GPU频率下降） 63C
Perf：性能状态，从P0（最大性能）到P12（最小性能），显示P0，最大性能
Pwr：Usager/Cap：GPU功耗，Usage表示用了多少，Cap表示总共多少 ， 79W / 80W
Persistence-M：持续模式状态，持续模式耗能大，为On
Bus-Id：GPU总线 00000000:01:00.0
Disp.A：Display Active，表示GPU是否初始化 Off
Memory-Usage：显存使用率 13140MiB / 16384MiB，表示已接近占满
Volatile GPU-UTil：GPU使用率，92%
Uncorr. ECC：是否开启错误检查和纠错技术，0/DISABLED，1/ENABLED，为N/A
Compute M：计算模式，0/DEFAULT，1/EXCLUSIVE_PROCESS，2/PROHIBITED，为Default
Processes：显示每个进程占用的显存使用率、进程号、占用的哪个GPU，/python3.10
GPU Memory Usage #该进程占用的显存。
Every 1.0s: nvidia-smi
Wed Apr 24 20:14:20 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.76.01 Driver Version: 552.22 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3080 ... On | 00000000:01:00.0 Off | N/A |
| N/A 63C P3 79W / 80W | 13140MiB / 16384MiB | 92% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 140468 C /main N/A |
+-----------------------------------------------------------------------------------------+
执行命令（ggml-model-q4_0.gguf）
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ ./main -m ./models/Llama-7b-Chinese/ggml-model-q4_0.gguf -n 512 --prompt "我给大家介绍一下中国"
Log start
main: build = 2038 (7013716)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1713953984
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3080 Ti Laptop GPU, compute capability 8.6, VMM: yes
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from ./models/Llama-7b-Chinese/ggml-model-q4_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = models
llama_model_loader: - kv 2: llama.context_length u32 = 2048
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 2
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 18: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 19: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_0: 225 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 2048
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 11008
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 2048
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = Q4_0
llm_load_print_meta: model params = 6.74 B
llm_load_print_meta: model size = 3.56 GiB (4.54 BPW)
llm_load_print_meta: general.name = models
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.11 MiB
llm_load_tensors: offloading 0 repeating layers to GPU
llm_load_tensors: offloaded 0/33 layers to GPU
llm_load_tensors: CPU buffer size = 3647.87 MiB
..................................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA_Host KV buffer size = 256.00 MiB
llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
llama_new_context_with_model: CUDA_Host input buffer size = 9.01 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 77.55 MiB
llama_new_context_with_model: graph splits (measure): 1
system_info: n_threads = 10 / 20 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
sampling:
repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp
generate: n_ctx = 512, n_batch = 512, n_predict = 512, n_keep = 0
我给大家介绍一下中国国内的许多电商平台，可是很多人都不知道什么时候会出现新的电商平台，因此为了方便大家使用，
Hinweis：虽然这些电商平台大部分都是在中国开始推出，但它们还是可以到达全球的。
### 1. 京东JD.com
京东JD.com是中国的最大电商平台，在中国开始推出的时候就已经有着相当较高的市场份领，为了保持这一状态，京东JD.com也不断投入资金去吸引更多的用户进来，现在他们已经成功地将自己从电子商务平台发展到了中国第一大的全线物流服务商。
京东JD.com也有相当较高的国际客户份领，可是由于他们的官网还没有支持外语版本，所以只能通过代理人来进行投放，这样就会导致外国用户很难了进行交易。
### 2. 微信小程序
微信小程序也是在中国最为人所知的一款
llama_print_timings: load time = 359.18 ms
llama_print_timings: sample time = 125.12 ms / 512 runs ( 0.24 ms per token, 4091.91 tokens per second)
llama_print_timings: prompt eval time = 1128.84 ms / 14 tokens ( 80.63 ms per token, 12.40 tokens per second)
llama_print_timings: eval time = 51984.61 ms / 511 runs ( 101.73 ms per token, 9.83 tokens per second)
llama_print_timings: total time = 53440.98 ms / 525 tokens
Log end
nvidia-smi命令实时查看指定GPU使用情况
Every 1.0s: nvidia-smi : Wed Apr 24 18:19:59 2024
Wed Apr 24 18:19:59 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.76.01 Driver Version: 552.22 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3080 ... On | 00000000:01:00.0 Off | N/A |
| N/A 61C P8 13W / 80W | 198MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 160829 C /main N/A |
+-----------------------------------------------------------------------------------------+
(Llama-7b-Chinese) :~/newmodels/llama.cpp$ ./main -m ./models/Llama-7b-Chinese/ggml-model-q4_0.gguf -n 512 --n-gpu-layers 100 --prompt "我给 大家介绍一下中国"
Log start
main: build = 2038 (7013716)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1713954147
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3080 Ti Laptop GPU, compute capability 8.6, VMM: yes
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from ./models/Llama-7b-Chinese/ggml-model-q4_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = models
llama_model_loader: - kv 2: llama.context_length u32 = 2048
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 2
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 18: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 19: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_0: 225 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 2048
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 11008
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 2048
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = Q4_0
llm_load_print_meta: model params = 6.74 B
llm_load_print_meta: model size = 3.56 GiB (4.54 BPW)
llm_load_print_meta: general.name = models
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.22 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors: CPU buffer size = 70.31 MiB
llm_load_tensors: CUDA0 buffer size = 3577.56 MiB
..................................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 256.00 MiB
llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
llama_new_context_with_model: CUDA_Host input buffer size = 9.01 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 77.55 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 8.80 MiB
llama_new_context_with_model: graph splits (measure): 3
system_info: n_threads = 10 / 20 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
sampling:
repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp
generate: n_ctx = 512, n_batch = 512, n_predict = 512, n_keep = 0
我给大家介绍一下中国的很多文化。 everybody knows about the chinese culture, but only a few people know about our traditional folk custom.
Today i want to tell you about one of China's traditional folk custom and its significance.
### 问题：
我今天要讲一个很多人都不知道的中国传统文化，该什么？这个文化是什么意思？
Today i want to tell you about one of China's traditional folk custom and its significance.
### 解题：
我们家族的很多年代以来，每逢某一月中有些天气特别质疑，家人都会举行一种活动，就是在桌子上放上大量的白发和胎光。我们称之为“寻骷髅”。
这个儿童时代的我对这件事情并不了解，后来才知道这是一种传统文化，由此揭开了一层中国古老的神话故事幽静的面纱。
在现代社会，人们如何在生产时间下保持职业操守？还有人如何在家庭裡保持教育作用和推动儿童成长？
这是我想说的那个传统文化。
### 解题：
我们家族的很多年代以来，每逢某一月中有些天气特别质疑，家人都会举行一种活动，就是在桌子上放上大量的白发和胎光。我们称之为“寻骷髅”。
这个儿童时代的我对这件事情并不
llama_print_timings: load time = 638.00 ms
llama_print_timings: sample time = 88.82 ms / 512 runs ( 0.17 ms per token, 5764.60 tokens per second)
llama_print_timings: prompt eval time = 59.77 ms / 14 tokens ( 4.27 ms per token, 234.23 tokens per second)
llama_print_timings: eval time = 8798.01 ms / 511 runs ( 17.22 ms per token, 58.08 tokens per second)
llama_print_timings: total time = 9093.05 ms / 525 tokens
Log end
nvidia-smi命令实时查看指定GPU使用情况
Wed Apr 24 18:21:54 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.76.01 Driver Version: 552.22 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3080 ... On | 00000000:01:00.0 Off | N/A |
| N/A 68C P0 78W / 80W | 4114MiB / 16384MiB | 77% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 166223 C /main N/A |
+-----------------------------------------------------------------------------------------+
eval time = 8798.01 ms / 511 runs ( 17.22 ms per token, 58.08 tokens per second)
llama_print_timings: total time = 9093.05 ms / 525 tokens
Log end
nvidia-smi命令实时查看指定GPU使用情况
Wed Apr 24 18:21:54 2024
±----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.76.01 Driver Version: 552.22 CUDA Version: 12.4 |
|-----------------------------------------±-----------------------±---------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=+======|
| 0 NVIDIA GeForce RTX 3080 … On | 00000000:01:00.0 Off | N/A |
| N/A 68C P0 78W / 80W | 4114MiB / 16384MiB | 77% Default |
| | | N/A |
±----------------------------------------±-----------------------±---------------------+
±----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 166223 C /main N/A |
±----------------------------------------------------------------------------------------+