Hugging Face's logo

Madras1
/
DebertaBioClass

Text Classification
Transformers
Safetensors
English
Portuguese
deberta-v2
biology
science
nlp
biomedical
filter
deberta
text-embeddings-inference
Model card Files
xet
 Community
Madras1 commited on
Commit
3a53a69
·
verified ·
1 Parent(s): b936aa4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -25,13 +25,12 @@ widget:
25
  - text: "New studies regarding CRISPR technology show promise in gene editing."
26
  example_title: "Genetics Example 🔬"
27
  ---
28
-
29
- # DebertaBioClass 🧬🔍
30
-
31
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
32
  [![Framework: PyTorch](https://img.shields.io/badge/Framework-PyTorch-orange.svg)](https://pytorch.org/)
33
  [![Base Model: DeBERTa-v3](https://img.shields.io/badge/Base%20Model-DeBERTa%20v3-blue.svg)](https://huggingface.co/microsoft/deberta-v3-base)
34
 
 
 
35
  **DebertaBioClass** is a fine-tuned DeBERTa-v3 model designed for **high-recall** filtering of biological texts. It excels at identifying biological content in large, noisy datasets, prioritizing "finding everything" even if it means capturing slightly more noise than other architectures.
36
 
37
  ## Model Details
 
25
  - text: "New studies regarding CRISPR technology show promise in gene editing."
26
  example_title: "Genetics Example 🔬"
27
  ---
 
 
 
28
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
29
  [![Framework: PyTorch](https://img.shields.io/badge/Framework-PyTorch-orange.svg)](https://pytorch.org/)
30
  [![Base Model: DeBERTa-v3](https://img.shields.io/badge/Base%20Model-DeBERTa%20v3-blue.svg)](https://huggingface.co/microsoft/deberta-v3-base)
31
 
32
+ # DebertaBioClass 🧬
33
+
34
  **DebertaBioClass** is a fine-tuned DeBERTa-v3 model designed for **high-recall** filtering of biological texts. It excels at identifying biological content in large, noisy datasets, prioritizing "finding everything" even if it means capturing slightly more noise than other architectures.
35
 
36
  ## Model Details