CHFLTM/gliner2-lora-custom

GLiNER2 LoRA Adapter

This is a LoRA adapter trained on top of fastino/gliner2-large-v1.

Usage

from gliner2 import GLiNER2

# Load base model
model = GLiNER2.from_pretrained("fastino/gliner2-large-v1")

# Load LoRA adapter
model.load_adapter("CHFLTM/gliner2-lora-custom")

# Use the model
text = "Your text here"
labels = ["person", "organization", "location"]
entities = model.predict_entities(text, labels, threshold=0.5)

print(entities)

Training

This adapter was trained using LoRA (Low-Rank Adaptation) with the following configuration:

• Base model: fastino/gliner2-large-v1
• LoRA rank: 16
• LoRA alpha: 32
• LoRA dropout: 0.1
• Target modules: encoder

Model Details

• Developed by: [Your Name/Organization]
• Model type: Named Entity Recognition (NER)
• Language: [Your language]
• License: [Your license]