tiiuae
/

Falcon3-7B-Instruct-1.58bit

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

Falcon3-7B-Instruct-1.58bit / tokenizer_config.json

Commit History

(fix): align quantized models tokenizers with un-quantized ones (#1)

84526f3
verified

ybelkada commited on Jan 13

Upload tokenizer

fecda51
verified

ybelkada commited on Dec 18, 2024

falcon3 release

cf63936

slimfrikha-tii commited on Dec 17, 2024