metadata

base_model: openai/gpt-oss-20b
datasets:
  - kingabzpro/dermatology-qa-firecrawl-dataset
library_name: transformers
model_name: gpt-oss-20b-dermatology-qa
tags:
  - generated_from_trainer
  - trl
  - sft
  - dermatology
  - medical
licence: license
license: apache-2.0
language:
  - en
pipeline_tag: text-generation

Model Card for gpt-oss-20b-dermatology-qa

This model is a fine-tuned version of openai/gpt-oss-20b on the kingabzpro/dermatology-qa-firecrawl-dataset dataset. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "How does the source suggest clinicians approach the diagnosis of rosacea?"

# Load pipeline
generator = pipeline(
    "text-generation",
    model="kingabzpro/gpt-oss-20b-dermatology-qa",
    device="cuda"  # or device=0
)


# Run inference (passing in chat-style format)
output = generator(
    [{"role": "user", "content": question}],
    max_new_tokens=200,
    return_full_text=False
)[0]

print(output["generated_text"])

# The source says that clinicians should use a combination of clinical signs and symptoms when diagnosing rosacea, rather than relying on a single feature.

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.21.0
Transformers: 4.55.4
Pytorch: 2.8.0.dev20250319+cu128
Datasets: 4.0.0
Tokenizers: 0.21.4

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}