Commit Graph

4 Commits (16bf4c022150fea303d23437b0190c46204e722c)

Author SHA1 Message Date
Wenhao Chen 75c5389037
[chat] fix compute_approx_kl (#4338) 2023-08-01 10:21:45 +08:00
yuxuan-lou 0991405361 [NFC] polish applications/Chat/coati/models/utils.py codestyle (#4277)
* [NFC] polish colossalai/context/random/__init__.py code style

* [NFC] polish applications/Chat/coati/models/utils.py code style
2023-07-26 14:12:57 +08:00
Wenhao Chen 9d02590c9a
[chat] refactor actor class (#3968)
* refactor: separate log_probs fn from Actor forward fn

* refactor: separate generate fn from Actor class

* feat: update unwrap_model and get_base_model
* unwrap_model returns model not wrapped by Strategy
* get_base_model returns HF model for Actor, Critic and RewardModel

* feat: simplify Strategy.prepare

* style: remove get_base_model method of Actor

* perf: tokenize text in batches

* refactor: move calc_action_log_probs to utils of model

* test: update test with new forward fn

* style: rename forward fn args

* fix: do not unwrap model in save_model fn of naive strategy

* test: add gemini test for train_prompts

* fix: fix _set_default_generate_kwargs
2023-06-13 13:31:56 +08:00
Fazzie-Maqianli b0ce5a1032
[Coati] first commit (#3283) 2023-03-28 20:25:36 +08:00