Downloads · 30 days
22
17% of all-time downloads
Meta-Llama-3-70B-AQLM-PV-1Bit-1x16
ISTA-DASLab/Meta-Llama-3-70B-AQLM-PV-1Bit-1x16
Meta-Llama-3-70B-AQLM-PV-1Bit-1x16 is a text generation model from ISTA-DASLab. Use it when you need the model to write or continue text. It is set up for transformers.
An official quantization of meta-llama/Meta-Llama-3-70B using PV-Tuning on top of AQLM .
All-time downloads
133
Public
Parameters
7B
49.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors13.9 GB · 100%
Parameter types
How the weights are stored.
I164.3B · 61%
Try a prompt
Model card
From the Hugging Face model README
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 16 weights. The 1x16g16 models require aqlm inference library v1.1.6 or newer:
pip install aqlm[gpu,cpu]>=1.1.6
| 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 | 1x16g8 | 4.57 | 21.9 | Link |
| meta-llama/Meta-Llama-3-70B (this) | 1x16g16 | 8.67 | 13 | 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.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Jun 5, 2024
- Updated
- Sep 14, 2024