IntraFind
/

Llama-3-SauerkrautLM-8b-16k-Instruct-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct

Model creator: VAGOsolutions
Original model: Meta-Llama-3-8B-Instruct
Quantized by: mayflowergmbh

This model is a variant of https://huggingface.co/mayflowergmbh/Llama-3-SauerkrautLM-8b-Instruct-AWQ extended to 16k context size by means of ROPE scaling.

Downloads last month: 13

Safetensors

Model size

1.98B params

Tensor type

I32

·

FP16

·

Inference Examples

Text Generation

Inference API (serverless) has been turned off for this model.