-
PTPReasoning/Qwen2.5-7B-Base-SFT-Clean-V2
Text Generation • 8B • Updated • 2 -
PTPReasoning/Qwen2.5-7B-Base-SFT-Baseline-V2
Text Generation • 8B • Updated • 1 -
PTPReasoning/Qwen2.5-7B-Base-RL-Clean-V2
Text Generation • 8B • Updated • 1 -
PTPReasoning/Qwen2.5-7B-Base-RL-Baseline
Text Generation • 8B • Updated • 1
ProgramTrace
non-profit
AI & ML interests
None defined yet.
-
PTPReasoning/Qwen2.5-7B-Base-SFT-Clean-V2
Text Generation • 8B • Updated • 2 -
PTPReasoning/Qwen2.5-7B-Base-SFT-Baseline-V2
Text Generation • 8B • Updated • 1 -
PTPReasoning/Qwen2.5-7B-Base-RL-Clean-V2
Text Generation • 8B • Updated • 1 -
PTPReasoning/Qwen2.5-7B-Base-RL-Baseline
Text Generation • 8B • Updated • 1
models 8
PTPReasoning/Llama-3.1-8B-RL-Clean-V2
8B • Updated
PTPReasoning/Llama-3.1-8B-RL-Baseline-V2
8B • Updated
PTPReasoning/Llama-3.1-8B-SFT-Baseline
Text Generation • 8B • Updated
PTPReasoning/Llama-3.1-8B-SFT-Clean-V2
Text Generation • 8B • Updated
PTPReasoning/Qwen2.5-7B-Base-RL-Clean-V2
Text Generation • 8B • Updated
• 1
PTPReasoning/Qwen2.5-7B-Base-RL-Baseline
Text Generation • 8B • Updated
• 1
PTPReasoning/Qwen2.5-7B-Base-SFT-Clean-V2
Text Generation • 8B • Updated
• 2
PTPReasoning/Qwen2.5-7B-Base-SFT-Baseline-V2
Text Generation • 8B • Updated
• 1
datasets 12
PTPReasoning/finqa
Viewer
• Updated
• 1.15k • 67
PTPReasoning/hotpot_qa
Viewer
• Updated
• 500 • 38
PTPReasoning/PubMedQA
Viewer
• Updated
• 1.5k • 7
PTPReasoning/MedCalc-Bench-v1.0
Viewer
• Updated
• 22.5k • 7 • 2
PTPReasoning/PTP-RL-ITL-Final-Clean-V2
Viewer
• Updated
• 19k • 3
PTPReasoning/PTP-SFT-ITL-Final-Baseline-V2
Viewer
• Updated
• 4.12k • 6
PTPReasoning/PTP-SFT-ITL-Final-Clean-V2
Viewer
• Updated
• 4.21k • 6
PTPReasoning/PTP-RL-MedCalc-Bench
Viewer
• Updated
• 9.34k • 4
PTPReasoning/PTP-RL-DAPO-EN
Viewer
• Updated
• 14.1k • 4
PTPReasoning/mmlu_pro_biology
Viewer
• Updated
• 717 • 4