Downloads · 30 days
109
1% of all-time downloads
Mixtral-8x7b-AQLM-2Bit-1x16-hf
ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf
Mixtral-8x7b-AQLM-2Bit-1x16-hf 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.
Official AQLM quantization of mistralai/Mixtral-8x7B-v0.1.
All-time downloads
13.8K
Public
Parameters
6.5B
26.2 GB on disk
Likes
23
Public
Repo makeup
Click a slice to open those files.
.safetensors13.1 GB · 100%
Parameter types
How the weights are stored.
I165.8B · 89%
Try a prompt
Model card
From the Hugging Face model README
Official AQLM quantization of mistralai/Mixtral-8x7B-v0.1.
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 | 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 (THIS) | 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.
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- Created
- Feb 8, 2024
- Updated
- Mar 11, 2024