arxiv:2606.05405
Jingxuan Fan
fjxdaisy
AI & ML interests
None yet
Recent Activity
updated a model about 15 hours ago
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step270 published a model about 15 hours ago
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step270 updated a model about 15 hours ago
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step240Organizations
models 19
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step270
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step240
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-rm-cc0-step210
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-rm-cc0-step180
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step210
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step180
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc0-step150
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-rm-cc0-step150
3B • Updated
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc01-step270
3B • Updated • 2
fjxdaisy/llama-3.2-3b-finemath-iclm-rm-cc01-step240
3B • Updated • 4
datasets 12
fjxdaisy/ssrm_700k
Viewer • Updated • 700k • 18 • 1
fjxdaisy/Skywork-Reward-Preference-80K-v0.2
Viewer • Updated • 77k • 16
fjxdaisy/finemath_part10_llama8b_actor_218step_rm_vllm
Viewer • Updated • 3.34k • 7
fjxdaisy/finemath_part9_llama8b_actor_218step_rm_vllm
Viewer • Updated • 3.32k • 7
fjxdaisy/finemath_part5_llama8b_actor_218step_rm
Viewer • Updated • 2.84k • 28
fjxdaisy/finemath_part6_llama8b_actor_218step_rm
Viewer • Updated • 2.83k • 32
fjxdaisy/finemath_part8_llama8b_actor_218step_rm_vllm
Viewer • Updated • 3.32k • 7
fjxdaisy/finemath_part7_llama8b_actor_218step_rm_vllm
Viewer • Updated • 3.34k • 10
fjxdaisy/rlhfpipeline_mix1_llamafactory
Viewer • Updated • 244k • 41
fjxdaisy/summarize_from_feedback_comparisons_pref
Viewer • Updated • 179k • 12