Wenhao Chen 3d8d5d0d58 [chat] use official transformers and fix some issues (#4117) ... * feat: remove on_learn_epoch fn as not used * revert: add _on_learn_epoch fn * feat: remove NaiveStrategy * test: update train_prompts tests * fix: remove prepare_llama_tokenizer_and_embedding * test: add lora arg * feat: remove roberta support in train_prompts due to runtime errs * feat: remove deberta & roberta in rm as not used * test: remove deberta and roberta tests * feat: remove deberta and roberta models as not used * fix: remove calls to roberta * fix: remove prepare_llama_tokenizer_and_embedding * chore: update transformers version * docs: update transformers version * fix: fix actor inference * fix: fix ci * feat: change llama pad token to unk * revert: revert ddp setup_distributed * fix: change llama pad token to unk * revert: undo unnecessary changes * fix: use pip to install transformers		2023-07-04 13:49:09 +08:00
..
base	[chat] refactor actor class (#3968)	2023-06-13 13:31:56 +08:00
bloom	[chat] remove lm model class (#3653)	2023-04-27 15:37:38 +08:00
gpt	[chat] remove lm model class (#3653)	2023-04-27 15:37:38 +08:00
llama	[chat] remove lm model class (#3653)	2023-04-27 15:37:38 +08:00
opt	[chat] remove lm model class (#3653)	2023-04-27 15:37:38 +08:00
__init__.py	[chat] remove lm model class (#3653)	2023-04-27 15:37:38 +08:00
generation.py	[chat] refactor actor class (#3968)	2023-06-13 13:31:56 +08:00
lora.py	[chat] add distributed PPO trainer (#3740)	2023-06-07 10:41:16 +08:00
loss.py	[chat]: add vf_coef argument for PPOTrainer (#3318)	2023-04-11 09:54:59 +08:00
utils.py	[chat] refactor actor class (#3968)	2023-06-13 13:31:56 +08:00