Active filters: YangyiYY
Text Generation • 7B • Updated • 177
• 5
YangyiYY/model_output_sft
Text Generation • 8B • Updated • 4
YangyiYY/model_output_sft2
Text Generation • 8B • Updated • 3
YangyiYY/model_output_dpo2
Text Generation • 8B • Updated • 5
YangyiYY/model_output_dpo_llama_data
Text Generation • 8B • Updated • 4
YangyiYY/model_output_sft_llama_preferred
Text Generation • 8B • Updated • 5
YangyiYY/model_output_sft_llama_rejected
Text Generation • 8B • Updated • 3
YangyiYY/model_output_sft_llama_preferred_mixed
Text Generation • 8B • Updated • 4
YangyiYY/Qwen2.5-1.5B-Open-R1-Distill
Updated
YangyiYY/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
YangyiYY/Qwen2.5-1.5B-Open-R1-GRPO
Updated
YangyiYY/Qwen2.5-VL_sft_tabmwp_textreason_RL
Updated
YangyiYY/Qwen2.5_sft_tabmwp_textreason_RL
3B • Updated • 20
YangyiYY/ckpt-evolve-5050-80
YangyiYY/ckpt-evolve-6040-80
YangyiYY/code_evolve_incorrect_50
YangyiYY/code_evolve_incorrect_T_69
Updated
YangyiYY/code_evolve_incorrect_T_69_N
YangyiYY/code_evolve_incorrect_NEWREWARD_r16
YangyiYY/14b_code_reasoning
YangyiYY/qwen2.5-7b-instruct-nct-ppo-actor
YangyiYY/qwen2.5-7b-instruct-nct-ppo-critic
YangyiYY/qwen3-8b-numina-math-ppo-actor
YangyiYY/qwen3-8b-code-ppo-actor