·
AI & ML interests
LLM Post-Training
Organizations
None yet
Renjie-Ranger/curriculum_128k_long-cot_Qwen2.5-7B-Instruct
Text Generation
• 8B • Updated
Renjie-Ranger/curriculum_128k_long-cot_Qwen2.5-1.5B-Instruct
Text Generation
• 2B • Updated
Renjie-Ranger/curriculum_128k_long-cot_Qwen2.5-3B-Instruct
Text Generation
• 3B • Updated
Renjie-Ranger/curriculum_8k_long-cot_gemma-3-1b-it
Text Generation
• 1.0B • Updated
• 1
Renjie-Ranger/gemma-3-1b-it
Updated
Renjie-Ranger/critique_s_math_good_bad_s_all_pairs_summary_s_Qwen3-4B-Base
4B • Updated
• 1
Renjie-Ranger/v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_ppo_mini_bsz_256-global_step_80
8B • Updated
• 4
Renjie-Ranger/v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_ppo_mini_bsz_256-global_step_60
8B • Updated
• 4
Renjie-Ranger/v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_ppo_mini_bsz_256-global_step_40
8B • Updated
• 3
Renjie-Ranger/v1-GPT5nano-critique-big_math_summary_C-plus_no_concise_ppo_mini_bsz_256-global_step_20
8B • Updated
• 5
Renjie-Ranger/1-GPT5nano-critique-big_math_summary_C-plus_no_concise_ppo_mini_bsz_256-global_step_140
8B • Updated
• 4
Renjie-Ranger/1-GPT5nano-critique-big_math_summary_C-plus_no_concise_ppo_mini_bsz_256-global_step_120
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_75
8B • Updated
• 5
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_70
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_65
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_60
8B • Updated
• 5
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_55
8B • Updated
• 4
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_50
8B • Updated
• 3
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_5
8B • Updated
• 3
Renjie-Ranger/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_normal-global_step_5
8B • Updated
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_40
8B • Updated
• 4
Renjie-Ranger/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_normal-global_step_45
Updated
Renjie-Ranger/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_normal-global_step_40
8B • Updated
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_35
8B • Updated
• 4
Renjie-Ranger/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_normal-global_step_35
8B • Updated
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_30
8B • Updated
• 2
Renjie-Ranger/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_normal-global_step_30
8B • Updated
Renjie-Ranger/CCFT-v1-GPT5nano-critique-math_no_concise_default-global_step_25
8B • Updated
• 4
Renjie-Ranger/v1-GPT5nano-critique-general_reasoner_summary_C-plus_no_concise_p-online-global_step_5
8B • Updated
• 4
Renjie-Ranger/GRPO-GPT5nano-critique-big_math_vanilla_partial_online_normal-global_step_25
8B • Updated
• 3