Token Classification
Transformers
Safetensors
English
medextractor
feature-extraction
information-extraction
span-extraction
medical
clinical
biomedical
ner
zero-shot
extractive-qa
custom_code
Instructions to use lion-ai/medextractor-liquid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lion-ai/medextractor-liquid with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="lion-ai/medextractor-liquid", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("lion-ai/medextractor-liquid", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
7 days ago
-
MedExtractor Liquid: uniform soup of six fine-tunes (locked tests in EVALUATION.md)
Verified signature502b731 -
README: model name in the zero-shot table header
Verified signature48c62ed
10 days ago
-
Faster extract(): batched end pointer, shared schema tokens, length-sorted batches (~6x throughput, same outputs)
Verified signature4679420 -
README: speed comparison on one GPU and CPU
Verified signature1b60e7a -
README: example figure (light/dark), Gemma 4 31B on all 15 corpora
Verified signature94f8b6c -
NOTICE: MedExtractor Liquid
Verified signaturede79d45 -
Rename to MedExtractor Liquid; English-only README
Verified signature57d13ac -
README: per-dataset zero-shot table with parameter counts
Verified signaturea158965 -
Shorter README; full results in EVALUATION.md
Verified signature3fee665 -
MedExtractor Nano v2: user-defined clinical fields, zero-shot biomedical NER (locked test results in the card)
Verified signature5fa0a4b
12 days ago
-
Model card: English usage example
Verified signaturead52683 -
Model card: single-model presentation
Verified signature605176b -
MedExtractor Nano v1: length soup of two specialization runs (zero-shot biomedical NER 55.2, OOD clinical 91.2%)
Verified signature539057f
14 days ago
-
Fix dtype mixing in end-pointer head when loaded in bf16
Verified signature0796b8a -
MedExtractor Nano (run ab1, model B)
Verified signaturee6cf6b5 -
initial commit
Verified signaturedf219f5