tiiuae
/

Falcon3-3B-Instruct-GPTQ-Int4

4-bit precision

Model card Files Files and versions

Falcon3-3B-Instruct-GPTQ-Int4 / tokenizer_config.json

Slim Frikha

(fix): align quantized models tokenizers with un-quantized ones (#3)

8437693 verified about 1 year ago

history contribute delete

365 kB

File too large to display, you can check the raw version instead.