How to use souuzaa/GLiNER2.5-Decide-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download souuzaa/GLiNER2.5-Decide-4bit --local-dir GLiNER2.5-Decide-4bit
How to use souuzaa/GLiNER2.5-Decide-4bit with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("souuzaa/GLiNER2.5-Decide-4bit") # Extract entities text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result)
https://huggingface.co/souuzaa/GLiNER2.5-Decide-4bit/resolve/main/tokenizer.json
hf download hf://souuzaa/GLiNER2.5-Decide-4bit/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/souuzaa/GLiNER2.5-Decide-4bit/resolve/main/tokenizer.json
