tiiuae
/

Falcon3-10B-Instruct-1.58bit

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

Falcon3-10B-Instruct-1.58bit

4 GB

3 contributors

History: 7 commits

ybelkada's picture

(fix): align quantized models tokenizers with un-quantized ones (#4)

4b61e88 verified about 1 year ago