corneille97
/

Llama-3-8B-4bits-turbo

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Edit model card

Model : Llama 3 8B 4bits

This is a Llama 3 8B model quantized on 4 bits using BitsandBytes. For fast upload enjoy !.

License : see https://huggingface.co/meta-llama/Meta-Llama-3-8B

Downloads last month: 69

Safetensors

Model size

4.65B params

Tensor type

FP16

·

F32

·

U8

·