Safetensors
llama
falcon3
8-bit precision
gptq
Falcon3-3B-Instruct-GPTQ-Int8 / tokenizer_config.json

Commit History

(fix): align quantized models tokenizers with un-quantized ones (#2)
65b0120
verified

slimfrikha-tii ybelkada commited on

Upload tokenizer
8728cc4
verified

ybelkada commited on