Safetensors
llama
falcon3
4-bit precision
gptq
Falcon3-7B-Instruct-GPTQ-Int4 / tokenizer_config.json

Commit History

(fix): align quantized models tokenizers with un-quantized ones
c49c87d
verified

ybelkada commited on

Upload tokenizer
766fa0d
verified

ybelkada commited on