AQLM+PV
Collection
Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852
•
21 items
•
Updated
•
18
An official quantization of meta-llama/Meta-Llama-3-70B using PV-Tuning on top of AQLM .
For this quantization, we used 1 codebook of 16 bits for groups of 8 weights.
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|---|---|---|---|---|
| meta-llama/Meta-Llama-3-8B | 1x16g8 | 6.99 | 4.1 | Link |
| meta-llama/Meta-Llama-3-8B | 1x16g16 | 9.43 | 3.9 | Link |
| meta-llama/Meta-Llama-3-70B (this) | 1x16g8 | 4.57 | 21.9 | Link |
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo. The original code for PV-Tuning can be found in the AQLM@pv-tuning branch.
- Downloads last month
- 132
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.