FlexingD
/

yarn-mistral-7B-64k-instruct-alpaca-cleaned-Q4

Text Generation

Inference Endpoints

text-generation-inference

8-bit precision

Model card Files Files and versions Community

Edit model card

Model Description

Model type: Text Generation
Language: English
Finetuned from model: NousResearch/Yarn-Mistral-7b-64k
Hardware Type: Ryzen 4090
Hours used: 37hs

Downloads last month: 17

Safetensors

Model size

7.24B params

Tensor type

F32

·

FP16

·

I8

·

Quantized from