Downloads · 30 days
0
chrisvoncsefalvay/smollm3-discharge-sentences-sft
smollm3-discharge-sentences-sft is a machine learning model from chrisvoncsefalvay. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This model is a fine-tuned version of HuggingFaceTB/SmolLM3-3B-Base for clinical sentence classification. It has been trained using TRL.
Downloads · 30 days
0
Access
Public
Updated Dec 7, 2025
Repo size
4.9 GB
Likes
0
Public
Click a slice to open those files.
.safetensors484 MB · 97%
From the Hugging Face model README
This model is a fine-tuned version of HuggingFaceTB/SmolLM3-3B-Base for clinical sentence classification. It has been trained using TRL.
This model classifies individual sentences from hospital discharge summaries into categories of follow-up actions. Given a sentence, it outputs a JSON object indicating which action categories apply.
from transformers import pipeline
sentence = "The patient was to follow up with Dr. Greene in three to four weeks."
generator = pipeline("text-generation", model="chrisvoncsefalvay/smollm3-discharge-sentences-sft", device="cuda")
output = generator([
{"role": "system", "content": "You are a clinical action item classifier..."},
{"role": "user", "content": f"Classify this sentence:\n\n{sentence}"}
], max_new_tokens=64, return_full_text=False)[0]
print(output["generated_text"])
# Output: {"categories": ["appointment"]}
Evaluated on 5,313 test samples from chrisvoncsefalvay/smol-discharge-sentences-sft.
| Metric | Score |
|---|---|
| JSON Validity | 97.5% |
| Exact Match Accuracy | 76.3% |
| Micro F1 | 0.631 |
| Macro F1 | 0.568 |
| Micro Precision | 0.734 |
| Micro Recall | 0.553 |
| Category | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| instructions | 0.931 | 0.460 | 0.616 | 1153 |
| appointment | 0.905 | 0.682 | 0.778 | 660 |
| medication | 0.354 | 0.707 | 0.471 | 239 |
| lab | 0.740 | 0.689 | 0.714 | 132 |
| procedure | 0.857 | 0.343 | 0.490 | 35 |
| imaging | 0.667 | 0.811 | 0.732 | 37 |
| other | 0.294 | 0.127 | 0.177 | 79 |
Strengths:
instructions (93.1%) and appointment (90.5%)appointment (0.778) and imaging (0.732)Limitations:
instructions (46.0%) and procedure (34.3%)other category (F1=0.177)This model was trained with SFT on the chrisvoncsefalvay/smol-discharge-sentences-sft dataset.
This model is intended for research purposes in clinical NLP, specifically for:
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}}
}