tiiuae
/

Falcon3-7B-Instruct-GPTQ-Int8

8-bit precision

Model card Files Files and versions

Falcon3-7B-Instruct-GPTQ-Int8

Commit History

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

77f20f2
verified

Slim Frikha

ybelkada commited on Jan 13

Upload tokenizer

50e6f29
verified

ybelkada commited on Dec 18, 2024

Update README.md (#1)

1915728
verified

Slim Frikha

karnakar commited on Dec 17, 2024

falcon3 release

0c45e91

slim.frikha commited on Dec 17, 2024