empirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bit

text-generation
Actively maintainedby empirischtech81915updated 1 month ago

A domain-optimized reasoning model built on DeepSeek-R1-Distill-Qwen-32B, refined through a multi-stage pipeline of GPTQ quantization-aware training and QLoRA fine-tuning. Achieves 84% on MedQA — within 4 points of GPT-4o — in a ~20GB package that fits on a single L40/L40s GPU.

README

license: cc-by-4.0 datasets: allenai/c4 language: en metrics: accuracy basemodel: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B pipelinetag: text-generation tags: gptq int4 quantized qlora medical medqa biology chemistry finance legal climate reasoning 4-bit model-index: name: Chaperone-Thinking-LQ-1.0 results: task: type: text-generation name: Medical QA dataset: name: MedQA type: medqa metrics: type: accuracy value: 84.0 task: type: text-generation name: Math Reasoning dataset: name: MATH-500…

Source attribution

  • HuggingFaceempirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bit

Related resources

In search enginers, rerankers are crucial for improving the accuracy of your retrieval system.

12.7K2 months ago
Python

Fine-tuned version of google/gemma-4-E4B-it across three professional domains — Medical, Legal, and Finance — using QLoRA (4-bit NF4) with Optuna-tuned hyperparameters, trained on Kaggle T4 GPU.

1K1 month ago
Python

HuatuoGPT-o1-7B

5031 year ago

In search engines, rerankers are crucial for improving the accuracy of your retrieval system.

150.1K2 weeks ago
Python