PFaithBench resistz/PFaithBench Viewer • Updated Oct 6 • 3.34k • 25 resistz/PairContext-Qwen3-4B 4B • Updated Oct 5 • 7 resistz/PairContext-Llama-3.2-3B-Instruct 4B • Updated Oct 5 • 10 resistz/PairContext-Llama-3.1-8B-Instruct 8B • Updated Oct 5 • 5
SFT on UltraChat200K Train one epoch SFT on UltraChat200K resistz/sft_Llama-3.1-8B_ultra200k_merged 8B • Updated Aug 13, 2025 • 5 resistz/sft_Qwen3-1.7B-Base_ultra200k Text Generation • 0.4B • Updated Aug 19, 2025 • 2 resistz/sft_Qwen3-8B-Base_ultra200k_lora32 Text Generation • Updated Aug 19, 2025 • 8 resistz/sft_Llama-3.2-1B_ultra200k Text Generation • 0.3B • Updated Aug 19, 2025 • 3
Test-time Calibration Learning (TTCL) Models Test-time calibration learning for large language model reasoning resistz/TTCL-MATH500-Qwen3-4B 4B • Updated Sep 28 • 21 resistz/TTCL-AMC23-Qwen3-4B 4B • Updated Sep 28 • 10 resistz/TTCL-AIME24-Qwen3-4B 4B • Updated Sep 28 • 9 resistz/TTCL-AIME25-Qwen3-4B 4B • Updated Sep 28 • 8
PFaithBench resistz/PFaithBench Viewer • Updated Oct 6 • 3.34k • 25 resistz/PairContext-Qwen3-4B 4B • Updated Oct 5 • 7 resistz/PairContext-Llama-3.2-3B-Instruct 4B • Updated Oct 5 • 10 resistz/PairContext-Llama-3.1-8B-Instruct 8B • Updated Oct 5 • 5
Test-time Calibration Learning (TTCL) Models Test-time calibration learning for large language model reasoning resistz/TTCL-MATH500-Qwen3-4B 4B • Updated Sep 28 • 21 resistz/TTCL-AMC23-Qwen3-4B 4B • Updated Sep 28 • 10 resistz/TTCL-AIME24-Qwen3-4B 4B • Updated Sep 28 • 9 resistz/TTCL-AIME25-Qwen3-4B 4B • Updated Sep 28 • 8
SFT on UltraChat200K Train one epoch SFT on UltraChat200K resistz/sft_Llama-3.1-8B_ultra200k_merged 8B • Updated Aug 13, 2025 • 5 resistz/sft_Qwen3-1.7B-Base_ultra200k Text Generation • 0.4B • Updated Aug 19, 2025 • 2 resistz/sft_Qwen3-8B-Base_ultra200k_lora32 Text Generation • Updated Aug 19, 2025 • 8 resistz/sft_Llama-3.2-1B_ultra200k Text Generation • 0.3B • Updated Aug 19, 2025 • 3