我們開源了 Chaperone-Thinking-LQ-1.0 — 一個 4-bit GPTQ + QLoRA 微調的 DeepSeek-R1-32B，在 MedQA 上達到 84% 準確率，僅需約 20GB

Hey everyone, We just open-sourced our reasoning model, Chaperone-Thinking-LQ-1.0, on Hugging Face. It's built on DeepSeek-R1-Distill-Qwen-32B but goes well beyond a simple quantization — here's what we actually did: The pipeline: 4-bit GPTQ quantization — compressed the model from ~60GB down to ~20GB Quantization-aware training (QAT) via GPTQ with calibration to minimize accuracy loss QLoRA fine-tuning on medical and scientific corpora Removed the adaptive identity layer for transparenc