YY Lin 62f4e2eb07 [Chat]Add Peft support & fix the ptx bug (#3433) ...

* Update ppo.py

Fix the bug of fetching wrong batch data

* Add peft model support in SFT and Prompts training

In stage-1 and stage-3, the peft model supports are added. So the trained artifacts will be only a small lora additions instead of the whole bunch of files.

* Delete test_prompts.txt

* Delete test_pretrained.txt

* Move the peft stuffs to a community folder.

* Move the demo sft to community

* delete dirty files

* Add instructions to install peft using source

* Remove Chinese comments

* remove the Chinese comments

2023-04-06 11:54:52 +08:00

..

dataset

[Chat] fix the tokenizer "int too big to convert" error in SFT training (#3453)

2023-04-06 09:30:28 +08:00

experience_maker

[Coati] first commit (#3283)

2023-03-28 20:25:36 +08:00

models

[chat]fix sft training for bloom, gpt and opt (#3418)

2023-04-04 09:46:23 +08:00

replay_buffer

[Coati] first commit (#3283)

2023-03-28 20:25:36 +08:00

trainer

[Chat]Add Peft support & fix the ptx bug (#3433)

2023-04-06 11:54:52 +08:00

utils

[Coati] first commit (#3283)

2023-03-28 20:25:36 +08:00

__init__.py

[Coati] first commit (#3283)

2023-03-28 20:25:36 +08:00