danieldk
/

Llama-3.1-8B-w4a16-int-24

compressed-tensors

Model card Files Files and versions Community

Edit model card

This model is only for testing. It's a reupload of nm-testing/Llama-3_1-8B_2of4_w4a16_gsm8k_256_8196_damp0_1_mse_llm_compressor, renamed to fit into Linux' path length for Unix domain sockets.

Downloads last month: 466

Safetensors

Model size

1.98B params

Tensor type

I32

·

BF16

·

FP16

·

I16

·

Inference API

Unable to determine this model's library. Check the docs .

Model tree for danieldk/Llama-3.1-8B-w4a16-int-24

Base model

meta-llama/Llama-3.1-8B

Quantized

(154)

this model