Active filters: CodeDPO
CodeDPO/llama3-RL-both-E2-0117-ckpt1624
8B • Updated • 4
CodeDPO/qwen_coder_2.5_rm_openrlhf
7B • Updated • 12
CodeDPO/qwen25-ins-7b-testcaserm-7b-reinforce-plus
8B • Updated • 6
CodeDPO/Qwen2.5-Coder-7B-binarized
7B • Updated • 15
CodeDPO/qwen25-ins-7b-coderm-7b-ppo
8B • Updated • 7
CodeDPO/qwen25-ins-7b-testcaserm-7b-reinforce-plus-binary
8B • Updated • 6
CodeDPO/qwen25-ins-7b-testcaserm-7b-reinforce-plus_new_dataset
8B • Updated • 6
CodeDPO/qwen25-coder-base-7b-testcaserm-7b-ppo-binary
8B • Updated • 9
CodeDPO/Qwen2.5-Coder-7B-new_with_margin_scalebt
7B • Updated • 12
CodeDPO/Qwen2.5-Coder-7B_with_margin_scalebt
7B • Updated • 11
CodeDPO/qwen25-coder-base-7b-testcaserm-7b-new-dataset-hard
8B • Updated • 7
CodeDPO/qwen25-ins-7b-coderm_new_margin_scalebt-7b-reinforce-plus-episode_1
Text Generation
• 8B • Updated • 12
CodeDPO/qwen25-ins-7b-coderm_new_margin_scalebt-7b-reinforce_plus_new_dataset
8B • Updated • 10
CodeDPO/qwen25-coder-inst-7b-testcaserm2-7b-reinforce_plus_new_dataset_hard
8B • Updated • 9
CodeDPO/Qwen2.5-Coder-Inst-7B-new-sigmoid
7B • Updated • 6
CodeDPO/Qwen2.5-Coder-Inst-7B-new_binarized_sigmoid
7B • Updated • 8
CodeDPO/qwen25-coder-ins-7b-coderm_new_sigmoid-c7b-reinforce-plus
8B • Updated • 6
CodeDPO/qwen25-coder-inst-7b-reinforce-plus_v2_mini_processed_r1
8B • Updated • 6
CodeDPO/qwen2.5-coder-inst-cold-start-R1
8B • Updated • 9
CodeDPO/qwen25-coder-base-7b-reinforce-plus_v2_mini_processed_r1_grpo_kl
8B • Updated • 16
CodeDPO/qwen25-coder-inst-7b-reinforce-plus_v2_mini_processed_r1_cold_start
8B • Updated • 15
CodeDPO/qwen25-coder-base-7b-reinforce-plus_v2_mini_processed_r1
8B • Updated • 14
CodeDPO/qwen25-coder-1.5b-inst-reinforce-plus_new_dataset_hard_r1
2B • Updated • 9
CodeDPO/AceCoder-Qwen2.5-Coder-1.5B-Ins-RM
2B • Updated • 7
• 1
CodeDPO/AceCodeRM-LLama3.1-8B
8B • Updated • 11
CodeDPO/AceCodeRM-LLama3.1-8B-v2
8B • Updated • 4
CodeDPO/qwen2.5-7b-coder_V2-200steps
8B • Updated • 10
CodeDPO/qwen2.5-7b-coder_V2-210steps
8B • Updated • 5
CodeDPO/qwen2.5-7b-coder_V2-220steps
8B • Updated • 8
CodeDPO/qwen2.5-7b-coder_V2-230steps
8B • Updated • 8