2dameneko
/

llava-v1.6-mistral-7b-hf-nf4

Image-Text-to-Text

4-bit precision

Model card Files Files and versions Community

Edit model card

llava-v1.6-mistral-7b-hf-nf4 is a bnb nf4 quant of llava-v1.6-mistral-7b-hf.

For batch processing you can use ide-cap-chan

All other features are inherited from the parent model.

Downloads last month: 68

Safetensors

Model size

4.03B params

Tensor type

F32

·

FP16

·

U8

·

Inference Examples

Image-Text-to-Text

Unable to determine this model's library. Check the docs .

Model tree for 2dameneko/llava-v1.6-mistral-7b-hf-nf4

Base model

llava-hf/llava-v1.6-mistral-7b-hf

Quantized

(2)

this model