Safetensors
llama
falcon3
4-bit precision
gptq
Falcon3-1B-Instruct-GPTQ-Int4 / tokenizer_config.json

Commit History

(fix): align quantized models tokenizers with un-quantized ones
b753f4c
verified

ybelkada commited on

fix chat_template for tools use (#1)
3015ae8
verified

Iheb-Chaabane commited on