andretisch
/

llava-saiga-8b-awq

4-bit precision

Model card Files Files and versions Community

Просто сделал квантизацию модели

Downloads last month: 2

Safetensors

Model size

2.31B params

Tensor type

I32

·

F16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for andretisch/llava-saiga-8b-awq

Base model

IlyaGusev/saiga_llama3_8b

Finetuned

deepvk/llava-saiga-8b

Quantized

(1)

this model