text-generation-webui/requirements_cpu_only_noavx2.txt

accelerate==0.27.*
colorama
datasets
einops
gradio==4.25.*
hqq==0.1.5
jinja2==3.1.2
lm_eval==0.3.0
markdown
numba==0.59.*
numpy==1.26.*
optimum==1.17.*
pandas
peft==0.8.*
Pillow>=9.5.0
psutil
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.39.*
tqdm
wandb

# API
SpeechRecognition==3.10.0
flask_cloudflared==0.0.14
sse-starlette==1.6.5
tiktoken

# llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
Update accelerate requirement from ==0.25.* to ==0.27.* (#5546) 2024-02-19 17:14:04 -05:00			`accelerate==0.27.*`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`colorama`
			`datasets`
			`einops`
Bump Gradio to 4.25 2024-04-05 12:22:44 -04:00			`gradio==4.25.*`
Bump HQQ to 0.1.5 2024-03-05 05:33:51 -05:00			`hqq==0.1.5`
Add requirement jinja2==3.1.* to fix error as described in issue #5240 (#5249) --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com> Co-authored-by: Rim <anonymous@mail.com> 2024-01-13 19:47:13 -05:00			`jinja2==3.1.2`
Pin lm_eval package version 2023-12-24 12:22:31 -05:00			`lm_eval==0.3.0`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`markdown`
Add numba to requirements.txt 2024-03-10 19:13:29 -04:00			`numba==0.59.*`
Update numpy requirement from ==1.24.* to ==1.26.* (#5490) 2024-02-13 14:26:35 -05:00			`numpy==1.26.*`
Update optimum requirement from ==1.16.* to ==1.17.* (#5548) 2024-02-19 17:15:21 -05:00			`optimum==1.17.*`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`pandas`
Revert "Update peft requirement from ==0.8.* to ==0.9.* (#5626)" This reverts commit 72a498ddd44a895205e53b5696742dc4ded9e12e. 2024-03-05 05:56:37 -05:00			`peft==0.8.*`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`Pillow>=9.5.0`
requirements: add psutil (#5819) 2024-04-06 22:02:20 -04:00			`psutil`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`pyyaml`
			`requests`
Add rich requirement 2023-12-20 00:58:36 -05:00			`rich`
Bump safetensors version 2024-02-04 21:40:25 -05:00			`safetensors==0.4.*`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`scipy`
			`sentencepiece`
			`tensorboard`
Bump transformers to 4.39 2024-03-28 22:40:31 -04:00			`transformers==4.39.*`
Improved instructions for AMD/Metal/Intel Arc/CPUs without AVCX2 2023-08-30 12:37:53 -04:00			`tqdm`
			`wandb`

Do not install extensions requirements by default (#5621) 2024-03-04 02:46:39 -05:00			`# API`
			`SpeechRecognition==3.10.0`
			`flask_cloudflared==0.0.14`
			`sse-starlette==1.6.5`
			`tiktoken`

Add comments 2023-09-24 09:08:39 -04:00			`# llama-cpp-python (CPU only, no AVX2)`
Downgrade llama-cpp-python to 0.2.56 2024-04-07 10:00:12 -04:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.56+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`