v0.0.3-alpha34
Add data loader for HF oasst1 (#2951)
add falcon model, and lima linear dropout increase (#3241)
sft8 training preparation (#2988)
Add trust_remote_code option to export_model.py (#3285)
Add return value in prepare_tensor (#3327)
Rl training (#2206)
readme.md dataset Table Formatting (#3219)
Add GPTNeoXRewardModel (#2182)
Fix typo in check_dataset_appearances.py (#3205)
fix bug
augment rank results for reward model and some other improvements for RM training (#2321)
Add LoRA and Prefix-Tuning as Modeling Options for Improved Memory Efficiency + performance (potentially) (#2840)