mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2026-03-02 03:24:08 +01:00
Compare commits
13 commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
910456ba31 | ||
|
|
d79cdc614c | ||
|
|
332fd40653 | ||
|
|
50a35b483c | ||
|
|
45fbec0320 | ||
|
|
b0968ed8b4 | ||
|
|
36747cf99c | ||
|
|
2fcbadec67 | ||
|
|
bb3b7bc197 | ||
|
|
6e2c4e9c23 | ||
|
|
a2ed640aa6 | ||
|
|
1066fe8c21 | ||
|
|
9530d3a6d8 |
|
|
@ -19,12 +19,14 @@
|
||||||
color: #d1d5db !important;
|
color: #d1d5db !important;
|
||||||
}
|
}
|
||||||
|
|
||||||
.chat .message-body :is(th, td) {
|
.chat .message-body :is(th, td),
|
||||||
|
.prose hr {
|
||||||
border-color: #40404096 !important;
|
border-color: #40404096 !important;
|
||||||
}
|
}
|
||||||
|
|
||||||
.dark .chat .message-body :is(th, td) {
|
.dark .chat .message-body :is(th, td),
|
||||||
border-color: #ffffff75 !important;
|
.dark .prose hr {
|
||||||
|
border-color: rgb(255 255 255 / 30%) !important;
|
||||||
}
|
}
|
||||||
|
|
||||||
.chat .message-body :is(p, ul, ol) {
|
.chat .message-body :is(p, ul, ol) {
|
||||||
|
|
|
||||||
17
css/main.css
17
css/main.css
|
|
@ -1797,3 +1797,20 @@ button#swap-height-width {
|
||||||
top: 0;
|
top: 0;
|
||||||
left: calc(100% - 174px);
|
left: calc(100% - 174px);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
table {
|
||||||
|
border-collapse: collapse;
|
||||||
|
}
|
||||||
|
|
||||||
|
table, tr, td, th, thead {
|
||||||
|
border: 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
td + td,
|
||||||
|
th + th { border-left: 1px solid; }
|
||||||
|
|
||||||
|
tr + tr td,
|
||||||
|
tr + tr th { border-top: 1px solid; }
|
||||||
|
|
||||||
|
thead + tbody tr:first-child td,
|
||||||
|
thead + tbody tr:first-child th { border-top: 1px solid; }
|
||||||
|
|
|
||||||
|
|
@ -83,7 +83,11 @@ def get_model_metadata(model):
|
||||||
|
|
||||||
if 'tokenizer.chat_template' in metadata:
|
if 'tokenizer.chat_template' in metadata:
|
||||||
template = metadata['tokenizer.chat_template']
|
template = metadata['tokenizer.chat_template']
|
||||||
|
if 'tokenizer.ggml.eos_token_id' in metadata:
|
||||||
eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']]
|
eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']]
|
||||||
|
else:
|
||||||
|
eos_token = ""
|
||||||
|
|
||||||
if 'tokenizer.ggml.bos_token_id' in metadata:
|
if 'tokenizer.ggml.bos_token_id' in metadata:
|
||||||
bos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.bos_token_id']]
|
bos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.bos_token_id']]
|
||||||
else:
|
else:
|
||||||
|
|
|
||||||
|
|
@ -1,12 +1,12 @@
|
||||||
accelerate==1.8.*
|
accelerate==1.8.*
|
||||||
audioop-lts<1.0; python_version >= "3.13"
|
audioop-lts<1.0; python_version >= "3.13"
|
||||||
bitsandbytes==0.48.*
|
bitsandbytes==0.49.*
|
||||||
colorama
|
colorama
|
||||||
datasets
|
datasets
|
||||||
diffusers==0.36.*
|
diffusers==0.36.*
|
||||||
einops
|
einops
|
||||||
fastapi==0.112.4
|
fastapi==0.112.4
|
||||||
flash-linear-attention==0.4.0
|
flash-linear-attention==0.4.*
|
||||||
html2text==2025.4.15
|
html2text==2025.4.15
|
||||||
huggingface-hub==0.36.0
|
huggingface-hub==0.36.0
|
||||||
jinja2==3.1.6
|
jinja2==3.1.6
|
||||||
|
|
@ -26,7 +26,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -42,8 +42,8 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# CUDA wheels
|
# CUDA wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
||||||
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
||||||
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -40,7 +40,7 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# AMD wheels
|
# AMD wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
||||||
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
|
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -40,7 +40,7 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# AMD wheels
|
# AMD wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
||||||
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
|
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -40,5 +40,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# Mac wheels
|
# Mac wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -40,5 +40,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# Mac wheels
|
# Mac wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -40,5 +40,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# llama.cpp (CPU only, AVX2)
|
# llama.cpp (CPU only, AVX2)
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -40,5 +40,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# llama.cpp (CPU only, no AVX2)
|
# llama.cpp (CPU only, no AVX2)
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
|
|
|
||||||
|
|
@ -1,12 +1,12 @@
|
||||||
accelerate==1.8.*
|
accelerate==1.8.*
|
||||||
audioop-lts<1.0; python_version >= "3.13"
|
audioop-lts<1.0; python_version >= "3.13"
|
||||||
bitsandbytes==0.48.*
|
bitsandbytes==0.49.*
|
||||||
colorama
|
colorama
|
||||||
datasets
|
datasets
|
||||||
diffusers==0.36.*
|
diffusers==0.36.*
|
||||||
einops
|
einops
|
||||||
fastapi==0.112.4
|
fastapi==0.112.4
|
||||||
flash-linear-attention==0.4.0
|
flash-linear-attention==0.4.*
|
||||||
html2text==2025.4.15
|
html2text==2025.4.15
|
||||||
huggingface-hub==0.36.0
|
huggingface-hub==0.36.0
|
||||||
jinja2==3.1.6
|
jinja2==3.1.6
|
||||||
|
|
@ -26,7 +26,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
@ -42,8 +42,8 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# CUDA wheels
|
# CUDA wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
||||||
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.18/exllamav3-0.0.18+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
||||||
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
||||||
|
|
|
||||||
|
|
@ -24,7 +24,7 @@ safetensors==0.7.*
|
||||||
scipy
|
scipy
|
||||||
sentencepiece
|
sentencepiece
|
||||||
tensorboard
|
tensorboard
|
||||||
torchao==0.14.*
|
torchao==0.15.*
|
||||||
transformers==4.57.*
|
transformers==4.57.*
|
||||||
triton-windows==3.5.1.post22; platform_system == "Windows"
|
triton-windows==3.5.1.post22; platform_system == "Windows"
|
||||||
tqdm
|
tqdm
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# CUDA wheels
|
# CUDA wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# AMD wheels
|
# AMD wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# AMD wheels
|
# AMD wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# Mac wheels
|
# Mac wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# Mac wheels
|
# Mac wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# llama.cpp (CPU only, AVX2)
|
# llama.cpp (CPU only, AVX2)
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# llama.cpp (CPU only, no AVX2)
|
# llama.cpp (CPU only, no AVX2)
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# CUDA wheels
|
# CUDA wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# Vulkan wheels
|
# Vulkan wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
|
|
|
||||||
|
|
@ -23,5 +23,5 @@ sse-starlette==1.6.5
|
||||||
tiktoken
|
tiktoken
|
||||||
|
|
||||||
# CUDA wheels
|
# CUDA wheels
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
|
||||||
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.71.0/llama_cpp_binaries-0.71.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue