Apppublic

sachiniyer/posttraining-practice

sourceHugging Faceupdated 8mo agoView on Hugging Face

0likes

models.py12 linesDownload Raw Back to root

1MODEL_IDS = [2    "sachiniyer/Qwen2.5-0.5B-GRPO-LLMJudge-Schwinn",3    "sachiniyer/Qwen2.5-0.5B-DPO-Schwinn",4    "sachiniyer/Qwen2.5-0.5B-PPO-Schwinn",5    "Qwen/Qwen2.5-0.5B",6    "sachiniyer/SmolLM2-DPO-Schwinn-SmolLM2-Base",7    "sachiniyer/SmolLM2-DPO-Schwinn-gpt-5-mini-base",8    "sachiniyer/SmolLM2-FT-SFT-Learning",9    "sachiniyer/DeepSeek-R1-LoRA-Finetuned",10    "sachiniyer/DeepSeek-R1-QLoRA-Finetuned",11]12