hugo/protocolos-clinicos-br-cpt-1gen-14b

CPT (1 generator, GPT-4.1-mini) — Qwen2.5-14B-Instruct

Qwen2.5-14B-Instruct continually pre-trained on synthetic data derived from Brazil's official clinical guidelines (PCDTs). Single generator: GPT-4.1-mini.

• Base model: Qwen/Qwen2.5-14B-Instruct
• Type: Full fine-tuned weights

Test-split accuracy

Benchmark	Accuracy
HealthBench-BR	69.6%
PCDT-QA	66.3%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("hugo/protocolos-clinicos-br-cpt-1gen-14b", torch_dtype="auto", device_map="auto")
tok   = AutoTokenizer.from_pretrained("hugo/protocolos-clinicos-br-cpt-1gen-14b")

Intended use & limitations

Research model for studying domain adaptation of LLMs to Brazilian clinical guidelines. Not a certified medical device. Even at the best accuracy reported in the paper, residual errors may involve consequential details (dosages, contraindications). Use only under qualified professional supervision.

Citation

See the paper and code at the project repository:

Code & paper: https://github.com/hugoabonizio/clinical-protocols-br