Downloads · 30 days
5
15% of all-time downloads
alyssavance/Meta-Llama-3.1-405B-HQQ-3bit-128g
Meta-Llama-3.1-405B-HQQ-3bit-128g is a machine learning model from alyssavance. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
3-bit HQQ quantized version of Meta-Llama-3.1-405B (base version). Quality will be degraded some, but should still be usable. Quantization parameters:
Downloads · 30 days
5
15% of all-time downloads
All-time downloads
33
Public
Repo size
186 GB
Likes
0
Public
Click a slice to open those files.
.pt186 GB · 100%
From the Hugging Face model README
3-bit HQQ quantized version of Meta-Llama-3.1-405B (base version). Quality will be degraded some, but should still be usable. Quantization parameters:
nbits=3, group_size=128, quant_zero=True, quant_scale=True, axis=0
Shards have been split with "split", to recombine:
cat qmodel_shard* > qmodel.pt