Official AQLM quantization of meta-llama/Llama-2-7b-hf.
For this quantization, we used 2 codebooks of 8 bits.
Selected evaluation results for this and other models:
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|---|---|---|---|---|
| Llama-2-7b | 1x16 | 5.92 | 2.4 | Link |
| Llama-2-7b | 2x8 | 6.69 | 2.2 | Link |
| Llama-2-7b (THIS) | 8x8 | 6.61 | 2.2 | Link |
| Llama-2-13b | 1x16 | 5.22 | 4.1 | Link |
| Llama-2-70b | 1x16 | 3.83 | 18.8 | Link |
| Llama-2-70b | 2x8 | 4.21 | 18.2 | Link |
| Mixtral-8x7b | 1x16 | 3.35 | 12.6 | Link |
| Mixtral-8x7b-Instruct | 1x16 | - | 12.6 | 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.
评论