Fazzie-Maqianli bd39877da4 support instrcut training (#3230)

2023-03-24 11:45:01 +08:00

..

base

support instrcut training (#3230)

2023-03-24 11:45:01 +08:00

bloom

[chatgpt] add supervised learning fine-tune code (#3183)

2023-03-22 09:59:42 +08:00

deberta

[chatgpt]add reward model code for deberta (#3199)

2023-03-22 19:09:39 +08:00

gpt

[chatgpt] add supervised learning fine-tune code (#3183)

2023-03-22 09:59:42 +08:00

llama

support instrcut training (#3230)

2023-03-24 11:45:01 +08:00

opt

[chatgpt] add supervised learning fine-tune code (#3183)

2023-03-22 09:59:42 +08:00

__init__.py

[chatgpt]Reward Model Training Process update (#3133)

2023-03-20 09:59:06 +08:00

generation_utils.py

change nn to models (#3032)

2023-03-07 16:34:22 +08:00

generation.py

[chatgpt] fix ppo training hanging problem with gemini (#3162)

2023-03-17 15:41:47 +08:00

lora.py

[chatgpt] fix lora save bug (#3099)

2023-03-10 17:58:10 +08:00

loss.py

[chatgpt]Reward Model Training Process update (#3133)

2023-03-20 09:59:06 +08:00

utils.py

change nn to models (#3032)

2023-03-07 16:34:22 +08:00