AQLM
Collection
AQLM quantized LLMs
•
20 items
•
Updated
•
46
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co./docs/hub/model-cards#model-card-metadata)
Official AQLM quantization of meta-llama/Llama-2-7b-hf.
For this quantization, we used 1 codebook of 16 bits.
Selected evaluation results for this and other models:
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|---|---|---|---|---|
| Llama-2-7b (THIS) | 1x16 | 5.92 | 2.4 | Link |
| Llama-2-7b | 2x8 | 6.69 | 2.2 | Link |
| Llama-2-7b | 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 |
UPD (20.02.2024). We applied global finetuning on top of quantized model and improved results compared to first revision.
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo.
- Downloads last month
- 8,503
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.