WaveCut
/

ruGPT-3.5-13B-4bit-bnb

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Edit model card

This is a 4-bit BitsAndBytes quantized version of ruGPT-3.5 13B, based on Gaivoronsky/ruGPT-3.5-13B-fp16

Downloads last month: 72

Safetensors

Model size

6.76B params

Tensor type

F32

·

BF16

·

U8

·