Downloads · 30 days
18
2% of all-time downloads
miqu-1-70b-AQLM-2Bit-1x16-hf
AlexWortega/miqu-1-70b-AQLM-2Bit-1x16-hf
miqu-1-70b-AQLM-2Bit-1x16-hf is a text generation model from AlexWortega. Use it when you need the model to write or continue text. It is set up for transformers.
AQLM quantization of 152334H/miqu-1-70b-sf.
All-time downloads
967
Public
Parameters
9.4B
18.8 GB on disk
Likes
27
Public
Repo makeup
Click a slice to open those files.
.safetensors18.8 GB · 100%
Parameter types
How the weights are stored.
I168.6B · 91%
Try a prompt
Model card
From the Hugging Face model README
AQLM quantization of 152334H/miqu-1-70b-sf.
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 | 6.31 | 2.4 | Link |
| Llama-2-7b | 2x8 | 7.98 | 2.2 | Link |
| Llama-2-7b | 8x8 | 7.83 | 2.2 | Link |
| Llama-2-13b | 1x16 | 5.41 | 4.1 | Link |
| Llama-2-70b | 1x16 | 3.96 | 18.8 | Link |
| Llama-2-70b | 2x8 | 4.83 | 18.2 | Link |
| Mixtral-8x7b | 1x16 | 4.37 | 12.6 | Link |
| miqu-1-70b (THIS) | 1x16 | 4.01 | 18.8 | 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
- llama
- Created
- Feb 12, 2024
- Updated
- Mar 10, 2024