MedCoast PRM: Medical reasoning evaluation model
1 min readupdated
Built on answerdotai/ModernBERT-base, this model evaluates intermediate reasoning chains in medical question-answering (medical QA). The checkpoints are designed exclusively for inference and evaluate pairwise reasoning quality. Input is limited to 2048 tokens. Checkpoints consist of dictionaries containing fp32 model_state and configuration.
Key features
- Based on answerdotai/ModernBERT-base
- Evaluates intermediate reasoning chains for medical QA
- Multiple checkpoint variants provided with different dsim and a parameters
- Designed for inference
What you can do
- Apply it to assess the quality of medical reasoning in QA tasks
- Use the PRMScorer class to load and initialize checkpoints
- Compare the accuracy of different checkpoint versions on validation data
Example
from huggingface_hub import hf_hub_download
from model.prm_scorer import PRMScorer
ckpt = hf_hub_download("zhongys97/MedCoast", "medcoast_prm_dsim0.75_a0.0.pt")
scorer = PRMScorer(api_keys_json_path="api_keys.json",
base_model_name="answerdotai/ModernBERT-base",
ft_model_path=ckpt)Read more
DetailsMaximum input length: 2048 tokens
Best validation accuracy (val pairwise acc): 0.6093 (dsim=0.85, a=0.0)
Checkpoint format: fp32 model_state and config
Base model: answerdotai/ModernBERT-base










Comments