models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
RLCR-lr1e-6-math-seed40RLCR-lr1e-6-math-seed41RLCR-lr1e-6-mathsmollm2-360m-boolq-calibration-grpo2-v1smollm2-360m-boolq-calibration-sft-v2smollm2-360m-boolq-calibration-sft-v1RLVR-mathRLCR-mathRLCR-lr1e-6-tabclong-mathRLCR-0.00005smCE-hotpot-seed41Llama-3.1-8B-Instruct-Self-CalibrationRLCR-0.00005smCE-hotpot-seed40gpt-oss-20b-2048-Calibration-FP8Qwen2.5-7B-Instruct-Self-Calibrationgpt-oss-120b-1024-Calibration-FP8DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibrationgpt-oss-120b-1024-Calibration-FP8Qwen2-72B-Instruct-mix-calibration-4b-exl2Qwen3-4B-4bit-DWQ-calibration-1332granite-8b-code-instruct-4k-2048-Calibration-FP8RLCR-0.00005smCE-hotpot-seed44Granite-34B-Code-Instruct-8k-2048-Calibration-FP8granite-20b-code-instruct-8k-2048-Calibration-FP8linguistic-calibration-extract-answersNextCoder-7B-2048-Calibration-FP8RLCR-0.25smCE-hotpotlinguistic-calibration-lc-sft-wdiffcalibration-only-v4NextCoder-14B-2048-Calibration-FP8linguistic-calibration-factuality-sft-wdiff