Instructions to use sumedh/biomedical_text_summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sumedh/biomedical_text_summarization with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="sumedh/biomedical_text_summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("sumedh/biomedical_text_summarization") model = AutoModelForSeq2SeqLM.from_pretrained("sumedh/biomedical_text_summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
tags:
- summarization
language:
- en
widget:
- text: Type your medical text here. 🤗
datasets:
- sumedh/MeQSum
co2_eq_emissions:
emissions: 3198.3976606503647
model-index:
- name: sumedh/biomedical_text_summarization
results:
- task:
type: summarization
name: Summarization
metrics:
- name: ROUGE-1
type: rouge
value: 39.4086
verified: true
- name: ROUGE-2
type: rouge
value: 12.8115
verified: true
- name: ROUGE-L
type: rouge
value: 21.9191
verified: true
- name: ROUGE-LSUM
type: rouge
value: 35.2431
verified: true
- name: loss
type: loss
value: 2.2001051902770996
verified: true
- name: gen_len
type: gen_len
value: 133.8541
verified: true
This model was created for text summarization for clinical text.
Check the index for evaluation scores on the ROUGE metric.