joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-4B_aime
Viewer • Updated • 860 • 37
Yang
joyfine
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
Self-Improvement of Large Language Models: A Technical Overview and Future Outlook upvoted a paper about 20 hours ago
Capability Self-Assessment: Teaching LLMs to Know Their Limits updated a dataset about 1 month ago
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-4B_aimeOrganizations
None yet
joyfine/router_SFT_self_generated_data_mmlu_pro_science_Qwen3-4B_aime
Viewer • Updated • 860 • 34
joyfine/router_PEFT_data_Math_5_shot_Qwen3-4B_aime
Viewer • Updated • 860 • 26
joyfine/router_PEFT_data_Math_5_shot_Qwen3-4B_gsm8k
Viewer • Updated • 1k • 47
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_OLMo-2-1124-13B-Instruct
Viewer • Updated • 3.27k • 14
joyfine/router_PEFT_data_Math_5_shot_Meta-Llama-3-8B-Instruct
Viewer • Updated • 2.26k • 10
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_Meta-Llama-3-8B-Instruct
Viewer • Updated • 3.27k • 23
joyfine/router_SFT_self_generated_data_mmlu_pro_science_Meta-Llama-3-8B-Instruct
Viewer • Updated • 3.27k • 429
joyfine/router_SFT_self_generated_data_Math_Meta-Llama-3-8B-Instruct
Viewer • Updated • 2.26k • 12
joyfine/router_SFT_larger_model_generated_data_Math_Meta-Llama-3-8B-Instruct
Viewer • Updated • 2.26k • 185
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Meta-Llama-3-8B-Instruct
Viewer • Updated • 3.27k • 15
joyfine/router_SFT_larger_model_generated_data_Math_OLMo-2-1124-13B-Instruct
Viewer • Updated • 2.26k • 9
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_OLMo-2-1124-13B-Instruct
Viewer • Updated • 3.27k • 39
joyfine/router_SFT_self_generated_data_mmlu_pro_science_OLMo-2-1124-13B-Instruct
Viewer • Updated • 3.27k • 14
joyfine/router_SFT_self_generated_data_Math_OLMo-2-1124-13B-Instruct
Viewer • Updated • 2.26k • 8
joyfine/router_PEFT_data_mmlu_pro_science_5_shot_shuffle_OLMo-2-1124-7B-Instruct
Viewer • Updated • 3.27k • 162
joyfine/router_SFT_self_generated_data_mmlu_pro_science_OLMo-2-1124-7B-Instruct
Viewer • Updated • 3.27k • 160
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_OLMo-2-1124-7B-Instruct
Viewer • Updated • 3.27k • 166
joyfine/router_SFT_larger_model_generated_data_Math_OLMo-2-1124-7B-Instruct
Viewer • Updated • 2.26k • 17
joyfine/router_SFT_self_generated_data_Math_OLMo-2-1124-7B-Instruct
Viewer • Updated • 2.26k • 8
joyfine/router_PEFT_data_Math_5_shot_OLMo-2-1124-13B-Instruct
Viewer • Updated • 2.26k • 94
joyfine/router_PEFT_data_Math_5_shot_OLMo-2-1124-7B-Instruct
Viewer • Updated • 2.26k • 83
joyfine/router_PEFT_data_Math_5_shot_OLMo-2-1124-13B-Instruct_rollout
Viewer • Updated • 2.04k • 17
joyfine/router_PEFT_data_Math_5_shot_OLMo-2-1124-7B-Instruct_rollout
Viewer • Updated • 1.83k • 53
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-14B
Viewer • Updated • 3.27k • 70 • 1
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-8B
Viewer • Updated • 3.27k • 18
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-4B
Viewer • Updated • 3.27k • 218 • 1
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-1.7B
Viewer • Updated • 3.27k • 70
joyfine/router_SFT_larger_model_generated_data_mmlu_pro_science_Qwen3-0.6B
Viewer • Updated • 3.27k • 42 • 1
joyfine/router_SFT_larger_model_generated_data_Math_Qwen3-14B
Viewer • Updated • 2.26k • 111