AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 00:07:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
35537ad3d1
text-generation-webui/requirements_amd.txt

45 lines
3.1 KiB
Plaintext
Raw Normal View History

Update accelerate requirement from ==0.24.* to ==0.25.* (#4810)
2023-12-04 23:36:01 +00:00
accelerate==0.25.*
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
colorama
datasets
einops
Bump gradio to 3.50.*
2023-10-23 04:20:41 +00:00
gradio==3.50.*
Bump hqq from 0.1.2 to 0.1.2.post1 (#5349)
2024-01-26 14:10:18 +00:00
hqq==0.1.2.post1
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>
2024-01-14 00:47:13 +00:00
jinja2==3.1.2
Pin lm_eval package version
2023-12-24 17:22:31 +00:00
lm_eval==0.3.0
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
markdown
Relax numpy version requirements (#4291)
2023-10-15 15:05:06 +00:00
numpy==1.24.*
Update optimum requirement from ==1.15.* to ==1.16.* (#4986)
2023-12-19 00:43:29 +00:00
optimum==1.16.*
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
pandas
Update peft requirement from ==0.6.* to ==0.7.* (#4886)
2023-12-12 05:31:30 +00:00
peft==0.7.*
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
Pillow>=9.5.0
pyyaml
requests
Add rich requirement
2023-12-20 05:58:36 +00:00
rich
Bump safetensors version
2024-02-05 02:40:25 +00:00
safetensors==0.4.*
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
scipy
sentencepiece
tensorboard
Bump transformers to 4.37
2024-01-22 12:07:12 +00:00
transformers==4.37.*
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
tqdm
wandb
# bitsandbytes
Use bitsandbytes==0.38.1 for AMD
2023-09-24 15:11:59 +00:00
bitsandbytes==0.38.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
Revert "Bump llama-cpp-python to 0.2.18 (#4611)" This reverts commit 923c8e25fb9d55fbf392cb07f7ddab1e0ee2b718.
2023-11-17 13:14:25 +00:00
# llama-cpp-python (CPU only, AVX2)
Bump llama-cpp-python to 0.2.39
2024-02-07 14:50:47 +00:00
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.39+cpuavx2-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-0.2.39+cpuavx2-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-0.2.39+cpuavx2-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-0.2.39+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
Revert "Bump llama-cpp-python to 0.2.18 (#4611)" This reverts commit 923c8e25fb9d55fbf392cb07f7ddab1e0ee2b718.
2023-11-17 13:14:25 +00:00
Create alternative requirements.txt with AMD and Metal wheels (#4052)
2023-09-24 12:58:29 +00:00
# AMD wheels
Bump llama-cpp-python to 0.2.39
2024-02-07 14:50:47 +00:00
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.39+rocm5.6.1-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/rocm/llama_cpp_python_cuda-0.2.39+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
Bump AutoGPTQ to 0.6.0 (adds Mixtral support)
2023-12-15 14:18:49 +00:00
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
Bump exllamav2 to 0.0.13.1 (#5463)
2024-02-07 16:17:04 +00:00
https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
Python 3.11, 3.9, 3.8 support (#4233) --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-10-21 00:13:33 +00:00
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
Reference in New Issue Copy Permalink