Qwen3-0.6B-Medical-Expert-abliterated API & Inference Endpoint

Dataset Preparation
- The FreedomIntelligence/medical-o1-reasoning-SFT dataset was used.
- Each example consists of medically relevant instructions or questions paired with detailed, step-by-step clinical reasoning responses.
- Prompts were structured to encourage safe, factual, and coherent medical reasoning chains.
Model Loading and Configuration
- Qwen3 base model weights were loaded via the unsloth library in bf16 precision.
- All model layers were fully updated (full_finetuning=True) to effectively adapt the model to medical reasoning and decision-making tasks.
Supervised Fine-Tuning
- Fine-tuning was conducted using the Hugging Face TRL library with the Supervised Fine-Tuning (SFT) approach.
- The model was trained to follow clinical instructions, interpret symptoms, and generate reasoned diagnoses or treatment suggestions.

The model’s ability to interpret medical instructions and generate step-by-step clinical reasoning has been significantly enhanced.
It produces responses that combine factual accuracy with transparent reasoning, making it useful in educational and assistive medical AI contexts.

This project is licensed under the Apache License 2.0. See the LICENSE file for details.

Dataset Preparation
- The FreedomIntelligence/medical-o1-reasoning-SFT dataset was used.
- Each example consists of medically relevant instructions or questions paired with detailed, step-by-step clinical reasoning responses.
- Prompts were structured to encourage safe, factual, and coherent medical reasoning chains.
Model Loading and Configuration
- Qwen3 base model weights were loaded via the unsloth library in bf16 precision.
- All model layers were fully updated (full_finetuning=True) to effectively adapt the model to medical reasoning and decision-making tasks.
Supervised Fine-Tuning
- Fine-tuning was conducted using the Hugging Face TRL library with the Supervised Fine-Tuning (SFT) approach.
- The model was trained to follow clinical instructions, interpret symptoms, and generate reasoned diagnoses or treatment suggestions.

The model’s ability to interpret medical instructions and generate step-by-step clinical reasoning has been significantly enhanced.
It produces responses that combine factual accuracy with transparent reasoning, making it useful in educational and assistive medical AI contexts.

This project is licensed under the Apache License 2.0. See the LICENSE file for details.

Qwen3-0.6B-Medical-Expert-abliterated