YangyiYY/qwen2.5-7b-instruct-nct-ppo-critic
7B • Updated • 12
Yangyi Chen
YangyiYY
AI & ML interests
Multimodal, Large Language Models
Recent Activity
updated a dataset about 14 hours ago
YangyiYY/rl-value-eval-code published a dataset about 14 hours ago
YangyiYY/rl-value-eval-code updated a dataset about 14 hours ago
YangyiYY/rl-value-confidence-train-codeOrganizations
None yet
YangyiYY/qwen2.5-7b-instruct-nct-ppo-actor
8B • Updated • 34
YangyiYY/14b_codechat
15B • Updated • 4
YangyiYY/14b_corrupt
15B • Updated • 4
YangyiYY/14b_nohistory
15B • Updated • 2
YangyiYY/14b_code_reasoning
15B • Updated • 6
YangyiYY/code_evolve_incorrect_NEWREWARD_r16
15B • Updated • 3
YangyiYY/code_evolve_incorrect_T_69_N
15B • Updated • 4
YangyiYY/code_evolve_incorrect_T_69
Updated
YangyiYY/code_evolve_incorrect_50
15B • Updated • 4
YangyiYY/ckpt-evolve-6040-80
15B • Updated • 3
YangyiYY/ckpt-evolve-5050-80
15B • Updated • 4
YangyiYY/ckpt-evolve-149
15B • Updated • 7
YangyiYY/ckpt-evolve-130
15B • Updated • 5
YangyiYY/ckpt-evolve-100
15B • Updated • 5
YangyiYY/Qwen2.5_sft_tabmwp_textreason_RL
3B • Updated • 7
YangyiYY/Qwen2.5-VL_sft_tabmwp_textreason_RL
Updated
YangyiYY/Qwen2.5-1.5B-Open-R1-GRPO
Updated
YangyiYY/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
YangyiYY/Qwen2.5-1.5B-Open-R1-Distill
Updated
YangyiYY/model_output_sft_llama_preferred_mixed
Text Generation • 8B • Updated • 4
YangyiYY/model_output_sft_llama_rejected
Text Generation • 8B • Updated • 5
YangyiYY/model_output_sft_llama_preferred
Text Generation • 8B • Updated • 3
YangyiYY/model_output_dpo_llama_data
Text Generation • 8B • Updated • 5
YangyiYY/model_output_dpo2
Text Generation • 8B • Updated • 3
YangyiYY/model_output_sft2
Text Generation • 8B • Updated • 4
YangyiYY/model_output_sft
Text Generation • 8B • Updated • 4
YangyiYY/SOLO-7B
Text Generation • 7B • Updated • 12 • 5