23 lines
853 B
Markdown
23 lines
853 B
Markdown
---
|
|
license: mit
|
|
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
|
datasets:
|
|
- FreedomIntelligence/medical-o1-reasoning-SFT
|
|
pipeline_tag: text-generation
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
---
|
|
|
|
# DeepSeek-R1-Medical-O1-QA
|
|
|
|
This is a fine-tuned version of the **deepseek-ai/DeepSeek-R1-Distill-Llama-8B** base model.
|
|
|
|
## Model Job
|
|
This model is specialized in text-based medical Question Answering (QA). It uses step-by-step reasoning to break down clinical scenarios, patient symptoms, and medical captions to provide clear answers.
|
|
|
|
## Dataset
|
|
Trained on the **FreedomIntelligence/medical-o1-reasoning-SFT** dataset to learn clinical chain-of-thought reasoning.
|
|
|
|
## Limitations
|
|
⚠️ This model is for research and educational purposes only. It cannot be used as a medical or diagnostic tool without a medical expert or doctor's supervision. |