qmd-training-scripts / train_1.7B_grpo.py

Commit History

Upload train_1.7B_grpo.py with huggingface_hub
bf6bf1b
verified

tobil commited on

Upload train_1.7B_grpo.py with huggingface_hub
36fb469
verified

tobil commited on

Add 1.7B GRPO training script
163aa9c
verified

tobil commited on