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

https://huggingface.co/empirischtech/DeepSeek-R1-Distill-Qwen-32B-gptq-4bit
Activeby empirischtech11316updated 4 months 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.

Sourced from

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

Related resources

> NEXUS domain specialist for medical Q&A and clinical reasoning — lightweight & uncensored.

Active1.6K2 months ago
Python

Model Size: 7B

Idle161 year ago

This repository contains a 4-bit GPTQ quantized version of google/medgemma-27b-text-it, optimized for high-throughput inference using vLLM and the Marlin kernel.

Active3462 months ago

QLoRA adapter for Llama-3.1-8B-Instruct, fine-tuned on PubMedQA for yes / no / maybe biomedical question answering (run5).

Active212 months ago
Python