Firworks
/

Llama-3.1-8B-Instruct-nvfp4

8-bit precision

compressed-tensors

Model card Files Files and versions

Llama-3.1-8B-Instruct-nvfp4 / model-00002-of-00002.safetensors

Firworks's picture

Add NVFP4 (W4A4) quantized checkpoint

fb2a133 verified about 1 month ago

history blame contribute delete

1.05 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Large File Pointer Details

( Raw pointer file )

SHA256:: 5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad
Pointer size:: 135 Bytes
Size of remote file:: 1.05 GB
Xet hash:: 206bcaf6cea61325668145ecbc3a35978d02337582f4100e332be430d4f1f7a4

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.