on-device-LLM-gpt-oss-20b

GPT-OSS 20B Fine-tuned for Medical Radiology Diagnosis

LoRA fine-tuned version of unsloth/gpt-oss-20b for medical radiology diagnosis tasks.

Model Details

• Base Model: unsloth/gpt-oss-20b
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Training Framework: Unsloth
• Task: Medical diagnosis from radiology reports
• Training Dataset: Eurorad medical cases

Installation

pip install unsloth peft transformers accelerate bitsandbytes

Usage

from unsloth import FastLanguageModel
from peft import PeftModel

# Load base model
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/gpt-oss-20b",
    dtype=None,
    max_seq_length=4096,
    load_in_4bit=True,
    full_finetuning=False,
)

# Load LoRA adapter
model = PeftModel.from_pretrained(
    model, 
    "omareng/on-device-LLM-gpt-oss-20b",
    is_trainable=False
)

# Enable inference mode
FastLanguageModel.for_inference(model)

Training Details

• Framework: Unsloth
• Dataset: Eurorad medical radiology cases
• Optimization: 4-bit quantization
• Sequence Length: 4096 tokens
• Adapter Size: 2.27 GB

Citation

[Citation information will be added upon publication]

Limitations

• Clinical Validation Required: This model has not been clinically validated and should not be used for actual patient diagnosis
• Not for Clinical Use: Not intended for direct patient care without clinical validation
• Research Purposes Only: Designed for research in medical AI and diagnostic systems
• May reflect biases present in training data
• Performance may vary across medical specialties
• Like all LLMs, may generate plausible but incorrect information

Contact

Issues: Please report to this repository

---

Disclaimer: This model is for research purposes only and has not been approved for clinical use. Always consult qualified healthcare professionals for medical decisions.