Zhuohan LiandJiCheng a60b353005 support sharding llama2-70b on more than 8 GPUs (#1209) ...

Co-authored-by: JiCheng <247153481@qq.com>

2023-10-02 15:26:33 -07:00

..

__init__.py

[Mistral] Mistral-7B-v0.1 support (#1196)

2023-09-28 10:41:03 -07:00

aquila.py

rope_theta and max_position_embeddings from config (#1096)

2023-09-20 13:35:11 -07:00

baichuan.py

rope_theta and max_position_embeddings from config (#1096)

2023-09-20 13:35:11 -07:00

bloom.py

Add Model Revision Support (#1014)

2023-09-13 15:20:02 -07:00

falcon.py

rope_theta and max_position_embeddings from config (#1096)

2023-09-20 13:35:11 -07:00

gpt2.py

Add Model Revision Support (#1014)

2023-09-13 15:20:02 -07:00

gpt_bigcode.py

Add Model Revision Support (#1014)

2023-09-13 15:20:02 -07:00

gpt_j.py

rope_theta and max_position_embeddings from config (#1096)

2023-09-20 13:35:11 -07:00

gpt_neox.py

rope_theta and max_position_embeddings from config (#1096)

2023-09-20 13:35:11 -07:00

internlm.py

rope_theta and max_position_embeddings from config (#1096)

2023-09-20 13:35:11 -07:00

llama.py

support sharding llama2-70b on more than 8 GPUs (#1209)

2023-10-02 15:26:33 -07:00

mistral.py

Fix Mistral model (#1220)

2023-09-28 10:44:05 -07:00

mpt.py

Add Model Revision Support (#1014)

2023-09-13 15:20:02 -07:00

opt.py

Add Model Revision Support (#1014)

2023-09-13 15:20:02 -07:00

qwen.py

Add rope_scaling to Qwen (#1210)

2023-09-28 00:49:23 -07:00