ホーム エクスプローラ ヘルプ
登録 サインイン
david
/
aphrodite-engine
同期ミラー https://github.com/PygmalionAI/aphrodite-engine
1
0
フォーク 0
ファイル 課題 0 Wiki
ツリー: 3a0fdf7b9b
ブランチ タグ
aphrodite-engin...
/
aphrodite
/
modeling
/
models
AlpinDale 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 ヶ月 前
..
__init__.py bbde979ecd DeepSeek-V2 (#579) 7 ヶ月 前
arctic.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
baichuan.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
bloom.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
chatglm.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
clip.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 ヶ月 前
commandr.py da6765c084 feat: lora support for commandr models 7 ヶ月 前
dbrx.py b2cb5a92e9 fix: missing cache_config for dbrx 7 ヶ月 前
decilm.py 56e0b8223c chore: add base class for LoRA-supported models 7 ヶ月 前
deepseek.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
deepseek_v2.py bbde979ecd DeepSeek-V2 (#579) 7 ヶ月 前
falcon.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
gemma.py b6ff0623a6 chore: clean up branding 7 ヶ月 前
gpt2.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
gpt_bigcode.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
gpt_j.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
gpt_neox.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
interfaces.py 85ef2fe8b1 chore: clean up placeholder symbols 7 ヶ月 前
internlm2.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
jais.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
llama.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
llama_embedding.py 50b7c13db0 refactor: attention selector (#552) 7 ヶ月 前
llava.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 ヶ月 前
llava_next.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 ヶ月 前
minicpm.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
mixtral.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
mixtral_quant.py b6ff0623a6 chore: clean up branding 7 ヶ月 前
mlp_speculator.py de7e6919c0 feat: support tied weights and input scale for MLPSpeculator 7 ヶ月 前
mpt.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
olmo.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
opt.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
orion.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
phi.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
phi3_small.py 696f2cd59c add phi3_small support with blocksparse attention 7 ヶ月 前
phi3v.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 ヶ月 前
qwen.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
qwen2.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前
qwen2_moe.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
stablelm.py 656459fd84 make fp8_e4m3 work on nvidia 7 ヶ月 前
starcoder2.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 7 ヶ月 前
xverse.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 ヶ月 前