Llama3-Taiwan-70B-Instruct-128K-AWQ-4bits leverages 4-bit quantized weights, processed with AutoAWQ, to significantly reduce GPU memory requirements.

References

Llama3-Taiwan-70B

For more information and detailed documentation, please refer to the links provided.

Downloads last month: 13

Safetensors

Model size

11.3B params

Tensor type

I32

FP16

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.