arxiv:2412.17743
zican dong
cjgs20017
AI & ML interests
None yet
Organizations
None yet
models 30
cjgs20017/qwen_rl_50
4B • Updated • 4
cjgs20017/qwen_rl_8k_28k_7k_all
4B • Updated • 3
cjgs20017/qwen_rl_8k_28k_7k
4B • Updated • 8
cjgs20017/qwen_rl_8k_28k_7k_low
4B • Updated • 3
cjgs20017/qwen_moe_test
Updated • 3
cjgs20017/deepseek_distill_sft
8B • Updated • 9
cjgs20017/mamba_reason
4.09M • Updated • 6
cjgs20017/mamba_longalign
4.09M • Updated • 6
cjgs20017/minicpm
8B • Updated • 8
cjgs20017/deepseek_qwen_rl
8B • Updated • 11
datasets 18
cjgs20017/fit-dataset
Updated • 17
cjgs20017/furebuttal
Preview • Updated • 57
cjgs20017/minicpm_sft
Viewer • Updated • 11.1k • 15 • 1
cjgs20017/rebuttal-dataset
Updated • 1
cjgs20017/hotpotqa_reason_ori
Viewer • Updated • 36.2k • 15
cjgs20017/hotpotqa_reason
Viewer • Updated • 5k • 9
cjgs20017/niah
Viewer • Updated • 2k • 3
cjgs20017/hotpotqa_28k
Viewer • Updated • 7.72k • 4
cjgs20017/hotpotqa_4k
Viewer • Updated • 3.46k • 5
cjgs20017/qwen3_small
Viewer • Updated • 7.14k • 9