license: apache-2.0
tags:

• unsloth
• trl
• sft
• medical
• reasoning
• abliterated
• baukit-abliterated
  datasets:
• FreedomIntelligence/medical-o1-reasoning-SFT
  language:
• en
  base_model:
• suayptalha/Qwen3-0.6B-Medical-Expert
  pipeline_tag: text-generation
  library_name: transformers

Qwen3-0.6B-Medical-Expert (Abliterated)

This project performs full fine-tuning on the Qwen3-0.6B language model to enhance its medical reasoning and clinical understanding capabilities. Training was conducted on the FreedomIntelligence/medical-o1-reasoning-SFT dataset using bfloat16 (bf16) precision for efficient optimization.
Additionally, it has been abliterated to make it steer away from censorship.

Training Procedure

1. 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.

2. 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.

3. 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.

Purpose and Outcome

• 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.

License

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

Support