mirror of https://github.com/hpcaitech/ColossalAI
9d02590c9a
* 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 |
||
|---|---|---|
| .. | ||
| callbacks | ||
| strategies | ||
| __init__.py | ||
| base.py | ||
| ppo.py | ||
| rm.py | ||
| sft.py | ||
| utils.py | ||