daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_680
Text Generation
•
2B
•
Updated
•
2
Daixuan Cheng
daixuancheng
AI & ML interests
I study LLMs, from Pre-Training to Agent.
Recent Activity
updated
a dataset
2 days ago
daixuancheng/llm-in-sandbox-rl
updated
a dataset
4 days ago
daixuancheng/llm-in-sandbox-bench
authored
a paper
10 days ago
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
Organizations
None yet
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_660
Text Generation
•
2B
•
Updated
•
2
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_640
Text Generation
•
2B
•
Updated
•
1
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_300
Text Generation
•
2B
•
Updated
•
2
daixuancheng/distill_1.5b_base_code_global_step_680
Text Generation
•
2B
•
Updated
•
2
daixuancheng/distill_1.5b_base_code_global_step_660
Text Generation
•
2B
•
Updated
•
2
daixuancheng/distill_1.5b_base_code_global_step_640
Text Generation
•
2B
•
Updated
•
2
daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step240
Text Generation
•
8B
•
Updated
•
2
daixuancheng/sac_static0.4_constrainbyAdv_step200
Text Generation
•
8B
•
Updated
•
2
daixuancheng/distill_1.5b_base_code_global_step_600
Text Generation
•
2B
•
Updated
•
2
daixuancheng/distill_1.5b_base_code_global_step_300
Text Generation
•
2B
•
Updated
•
2
daixuancheng/sac_static0.4_constrainbyAdv_step180
Text Generation
•
8B
•
Updated
•
2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step160_crtic
Text Generation
•
8B
•
Updated
•
2
daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step200
Text Generation
•
8B
•
Updated
•
2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-160_critic
Text Generation
•
8B
•
Updated
•
2
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step140
Text Generation
•
8B
•
Updated
•
2
daixuancheng/sac_static0.1_constrainbyAdv_step140
Text Generation
•
8B
•
Updated
•
2
daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step280
Text Generation
•
8B
•
Updated
•
2
daixuancheng/rerun_qwen-math-7b_noSuffix_base_step240
Text Generation
•
8B
•
Updated
•
2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step160_actor
Text Generation
•
8B
•
Updated
•
2
daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step240
Text Generation
•
8B
•
Updated
•
2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-160_actor
Text Generation
•
8B
•
Updated
•
2
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step200
Text Generation
•
8B
•
Updated
•
3
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step200_crtic
Text Generation
•
8B
•
Updated
•
2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-200_critic
Text Generation
•
8B
•
Updated
•
2
daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step200
Text Generation
•
8B
•
Updated
•
2
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step180
Text Generation
•
8B
•
Updated
•
2
daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step240
Text Generation
•
8B
•
Updated
•
2
daixuancheng/fix-entropy-1e-3_train_math_global_step_200
Text Generation
•
8B
•
Updated
•
1
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step200_actor
Text Generation
•
8B
•
Updated
•
2