sarimahsan101/qwen2.5-0.5b-detox-ppo
055
readme
Upload assets/ppo_reward_curve.png with huggingface_hub
Upload README.md with huggingface_hub
Upload tokenizer
PPO toxicity-reduction fine-tune (GPT-2 + Detoxify reward)
initial commit
readme
Upload assets/ppo_reward_curve.png with huggingface_hub
Upload README.md with huggingface_hub
Upload tokenizer
PPO toxicity-reduction fine-tune (GPT-2 + Detoxify reward)
initial commit