FlippyDora/Qwen2.5-Math-1.5B-raft-pp_numina_math-step_60
2B • Updated • 7
Jiarui Yao
FlippyDora
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos upvoted a paper 5 days ago
Selecting Diverse SFT Traces Improves Post-RL Generalization upvoted a paper 16 days ago
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video GenerationOrganizations
FlippyDora/Qwen2.5-Math-1.5B-raft-vanilla_numina_math-step_40
2B • Updated • 14
FlippyDora/Qwen2.5-Math-1.5B-raft-pp_numina_math-step_40
2B • Updated • 4
FlippyDora/Qwen2.5-Math-1.5B-raft-vanilla_numina_math-step_20
2B • Updated • 4
FlippyDora/Qwen2.5-Math-1.5B-raft-pp_numina_math-step_20
2B • Updated • 11
FlippyDora/Qwen1.5B-Inst_numina_raft1_orig_eos
Text Generation • 2B • Updated • 17
FlippyDora/qwen_sft_1
Text Generation • 8B • Updated • 20
FlippyDora/qwen_sft_2
Text Generation • 8B • Updated • 9
FlippyDora/Qwen_numina_raft3_orig_eos
Text Generation • 8B • Updated • 12
FlippyDora/Qwen_numina_raft2_orig_eos
Text Generation • 8B • Updated • 15
FlippyDora/3B_rpr_mixtureBT_criteria_loadBalance0.5_epoch5_k10
3B • Updated • 1
FlippyDora/3B_rpr_mixtureBT_attr_loadBalance0.5_epoch5_k5
3B • Updated • 2
FlippyDora/3B_rpr_mixtureBT_attr_loadBalance0.5_epoch5_k10
3B • Updated • 2
FlippyDora/3B_mixtureBT_rpr_criteria_k5_epoch5_loadBalance0.5
3B • Updated • 1
FlippyDora/3B_mixtureBT_helpsteer2_pkusafe_attr_heads6_loadBalance0.5
3B • Updated • 2
FlippyDora/3B_mixtureBT_rpr_criteria_epoch5_loadBalance0.5
3B • Updated • 2
FlippyDora/3B_rpr_mixtureBT_attr_loadBalance0.5
3B • Updated • 2
FlippyDora/3B_helpsteer2_mixtureBT_attr_loadBalance0.5
3B • Updated • 2
FlippyDora/CoT_Translator
7B • Updated • 4
FlippyDora/CoT_Prover
7B • Updated • 2
FlippyDora/dpo_rm
3B • Updated • 3
FlippyDora/dpo_remove
3B • Updated • 4
FlippyDora/origin_preference700k
3B • Updated • 9
FlippyDora/MixtureBT_preference700k_LoadBalance0.5
3B • Updated • 9
FlippyDora/MathLLM-StatementTranslator-7B-v0.1
7B • Updated • 13
FlippyDora/MixtureBT_Helpsteer2_LoadBalance0.5
3B • Updated • 3
FlippyDora/step_dpo_mistral_lr1e-7_step200
7B • Updated • 4
FlippyDora/step_dpo_mistral_lr1e-7_step100
7B • Updated • 13
FlippyDora/mdpo
3B • Updated • 2
FlippyDora/mdpo_guess_cities
3B • Updated • 4