Downloads · 30 days
37
1% of all-time downloads
Phi-3-mini-4k-instruct-AQLM-PV-2Bit-1x16-hf
ISTA-DASLab/Phi-3-mini-4k-instruct-AQLM-PV-2Bit-1x16-hf
Phi-3-mini-4k-instruct-AQLM-PV-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 quantization of Mistral-7B-v0.1 using PV-Tuning on top of AQLM.
All-time downloads
4.1K
Public
Parameters
718M
2.9 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
Parameter types
How the weights are stored.
I16453M · 63%
Try a prompt
Model card
From the Hugging Face model README
Official quantization of Mistral-7B-v0.1 using PV-Tuning on top of AQLM.
For this quantization, we used 1 codebook of 16 bits for groups of 8 weights.
Results (0-shot acc):
Results:
| Model | Quantization | ArcC | ArcE | Hellaswag | PiQA | Winogrande | Model size, Gb |
|---|---|---|---|---|---|---|---|
| microsoft/Phi-3-mini-4k-instruct | None | 0.5529 | 0.8325 | 0.6055 | 0.8020 | 0.7364 | 7.6 |
| 1x16 | 0.5051 | 0.7950 | 0.5532 | 0.7949 | 73.01 | 1.4 |
You can also find Phi-3-medium models compressed with AQLM+PV: 2-bit and 1-bit
The 1x16g16 (1-bit) models are on the way, as soon as we update the inference lib with their respective kernels.
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
- phi3
- Languages
- en
- Created
- May 29, 2024
- Updated
- Aug 3, 2024