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