|
|
1 maand geleden | |
|---|---|---|
| .. | ||
| deepspeed_zero3.yaml | c88e10fab6 grpo llama 3.2 3b with 3 reward functions | 1 maand geleden |
| grpo-llama323b-text2sql.yaml | 57c05170eb added llm as a judge reward func | 1 maand geleden |
| grpo_text2sql.py | 57c05170eb added llm as a judge reward func | 1 maand geleden |
| requirements.txt | 57c05170eb added llm as a judge reward func | 1 maand geleden |