RLCM Official Huggingface repo for the paper: Process Supervision of Confidence Margin for Calibrated LLM Reasoning Melodramas/RLCM-DeepSeek-R1-Distill-Qwen-7B 8B • Updated Jun 11 • 10 Melodramas/RLCM-Qwen3-4B-Instruct 4B • Updated Jun 11 • 4
RLCM Official Huggingface repo for the paper: Process Supervision of Confidence Margin for Calibrated LLM Reasoning Melodramas/RLCM-DeepSeek-R1-Distill-Qwen-7B 8B • Updated Jun 11 • 10 Melodramas/RLCM-Qwen3-4B-Instruct 4B • Updated Jun 11 • 4