shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think Text Generation • 1B • Updated 21 days ago • 267
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think Text Generation • 1B • Updated 21 days ago • 267
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean Text Generation • 1B • Updated 21 days ago • 172
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean Text Generation • 1B • Updated 21 days ago • 172
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think Text Generation • 1B • Updated 22 days ago • 187
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think Text Generation • 1B • Updated 22 days ago • 187
Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection Paper • 2505.17558 • Published May 23, 2025 • 15
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models Paper • 2502.14302 • Published Feb 20, 2025 • 9