AQLM+PV
Collection
Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852
•
25 items
•
Updated
•
18
An official quantization of meta-llama/Meta-Llama-3-8B using PV-Tuning on top of AQLM .
For this quantization, we used 1 codebook of 16 bits for groups of 8 weights.
Note that a large portion of this model are the 16-bit embeddings/logits matrices. You can significantly reduce the model footprint by quantizing these matrices, e.g. using bitsandbytes LLM.int8 or NF4 formats. This does not require additional training
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|---|---|---|---|---|
| meta-llama/Meta-Llama-3-8B (this) | 1x16g8 | 6.99 | 4.1 | Link |
| meta-llama/Meta-Llama-3-8B | 1x16g16 | 9.43 | 3.9 | Link |
| meta-llama/Meta-Llama-3-70B | 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
- 57
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.