daixuancheng/4-24-30BA3B-s233-final
31B • Updated
Daixuan Cheng
daixuancheng
AI & ML interests
I study LLMs, from Pre-Training to Agent.
Recent Activity
updated a model about 4 hours ago
daixuancheng/4-24-30BA3B-s233-final published a model about 5 hours ago
daixuancheng/4-24-30BA3B-s233-final updated a model about 11 hours ago
daixuancheng/4-23_docker_rbs32_model-Coder_step15Organizations
None yet
daixuancheng/4-23_docker_rbs32_model-Coder_step15
Text Generation • 31B • Updated
daixuancheng/0418_17K_filtered_10K_reward0.5_4b_inst
4B • Updated • 12
daixuancheng/4b-0404-2k
4B • Updated • 14
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL
4B • Updated • 548 • 1
daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL
9B • Updated • 1
daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard
9B • Updated • 2
daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio
9B • Updated • 2
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20
9B • Updated • 5
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36
9B • Updated • 3
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4
9B • Updated • 11
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10
9B • Updated • 1
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_actor
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_actor
Text Generation • 8B • Updated • 1
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_critic
Text Generation • 8B • Updated • 3
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_critic
Text Generation • 8B • Updated • 3
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-60_critic
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_critic
Text Generation • 8B • Updated • 4
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step80_crtic
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_crtic
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_crtic
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_crtic
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_actor
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-60_actor
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_actor
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_actor
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_actor
Text Generation • 8B • Updated • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step80_actor
Text Generation • 8B • Updated • 2
daixuancheng/sac_static0.4_constrainbyAdv_step80
Text Generation • 8B • Updated • 2
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step80
Text Generation • 8B • Updated • 2