Kezdőlap Felfedezés Súgó
Regisztráció Bejelentkezés
david
/
aphrodite-engine
tükrözi: https://github.com/PygmalionAI/aphrodite-engine
1
0
Másolás 0
Fájlok Problémák 0 Wiki
Fa: 3a0fdf7b9b
Branch-ok Tag-ek
aphrodite-engin...
/
aphrodite
/
modeling
/
models
AlpinDale 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 hónapja
..
__init__.py bbde979ecd DeepSeek-V2 (#579) 7 hónapja
arctic.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
baichuan.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
bloom.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
chatglm.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
clip.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 hónapja
commandr.py da6765c084 feat: lora support for commandr models 7 hónapja
dbrx.py b2cb5a92e9 fix: missing cache_config for dbrx 7 hónapja
decilm.py 56e0b8223c chore: add base class for LoRA-supported models 7 hónapja
deepseek.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
deepseek_v2.py bbde979ecd DeepSeek-V2 (#579) 7 hónapja
falcon.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
gemma.py b6ff0623a6 chore: clean up branding 7 hónapja
gpt2.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
gpt_bigcode.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
gpt_j.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
gpt_neox.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
interfaces.py 85ef2fe8b1 chore: clean up placeholder symbols 7 hónapja
internlm2.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
jais.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
llama.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
llama_embedding.py 50b7c13db0 refactor: attention selector (#552) 7 hónapja
llava.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 hónapja
llava_next.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 hónapja
minicpm.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
mixtral.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
mixtral_quant.py b6ff0623a6 chore: clean up branding 7 hónapja
mlp_speculator.py de7e6919c0 feat: support tied weights and input scale for MLPSpeculator 7 hónapja
mpt.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
olmo.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
opt.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
orion.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
phi.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
phi3_small.py 696f2cd59c add phi3_small support with blocksparse attention 7 hónapja
phi3v.py 3a0fdf7b9b chore: remove `image_input_type` from VLM config 7 hónapja
qwen.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
qwen2.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja
qwen2_moe.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
stablelm.py 656459fd84 make fp8_e4m3 work on nvidia 7 hónapja
starcoder2.py ac79d115b3 add guards for prefix caching, fp8, chunked, etc 7 hónapja
xverse.py c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 hónapja