arxiv:2412.17743
zican dong
cjgs20017
AI & ML interests
None yet
Recent Activity
upvoted a paper 22 days ago
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training upvoted a paper 22 days ago
SWE-World: Building Software Engineering Agents in Docker-Free Environments published
a model 2 months ago
cjgs20017/mistral_128k Organizations
None yet
models 20
cjgs20017/mamba_reason
4.09M • Updated
cjgs20017/mamba_longalign
4.09M • Updated
cjgs20017/minicpm
8B • Updated
• 1
cjgs20017/deepseek_qwen_rl
8B • Updated
cjgs20017/deepseek_qwen_p
8B • Updated
• 2
cjgs20017/deepseek_qwen_new
Updated
cjgs20017/llama
8B • Updated
• 1
cjgs20017/qwen3_small_new_04
2B • Updated
cjgs20017/qwen3_4b_low_large_long_179
4B • Updated
cjgs20017/qwen3_small
2B • Updated
• 1
datasets 14
cjgs20017/hotpotqa_reason_ori
Viewer
• Updated
• 36.2k • 10
cjgs20017/hotpotqa_reason
Viewer
• Updated
• 5k • 7
cjgs20017/niah
Viewer
• Updated
• 2k • 5
cjgs20017/hotpotqa_28k
Viewer
• Updated
• 7.72k • 19
cjgs20017/hotpotqa_4k
Viewer
• Updated
• 3.46k • 7
cjgs20017/qwen3_small
Viewer
• Updated
• 7.14k • 7
cjgs20017/deepseek_still_rl_with_loss_new
Viewer
• Updated
• 6.3k • 6
cjgs20017/deepseek_entropy_75
Viewer
• Updated
• 7.42k • 14
cjgs20017/deepseek_entropy_new
Viewer
• Updated
• 15.6k • 10
cjgs20017/qwen_long
Viewer
• Updated
• 7.14k • 6