---
base_model: unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---

# DeepSeek R1 Medical Reasoning

- **Finetuned from model:** [unsloth/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B)

This model was fine-tuned for medical reasoning using [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library, achieving 2x faster training.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

## Model Details

- **Fine-tuning task**: Medical reasoning with step-by-step chain-of-thought explanations
- **Training dataset**: [Medical reasoning dataset](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT) (500 examples)
- **Training metrics**:
  - Final loss: 1.3269
  - Training runtime: 2191.2041 seconds
  - Total FLOPs: 4.01e+16
  - Epochs completed: 1.896