update to transfomers 4.52
Browse filesSigned-off-by: n1ck-guo <[email protected]>
README.md
CHANGED
@@ -6,11 +6,15 @@ base_model:
|
|
6 |
## Model Details
|
7 |
|
8 |
This model is an int4 model with group_size 128 and symmetric quantization of [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round). Load the model with revision="e289950" to use AutoGPTQ format.
|
|
|
|
|
|
|
|
|
|
|
9 |
## How To Use
|
10 |
### INT4 Inference
|
11 |
|
12 |
```python
|
13 |
-
from auto_round import AutoRoundConfig ##must import for auto-round format
|
14 |
import torch
|
15 |
from PIL import Image
|
16 |
from transformers import AutoProcessor, AutoModelForVision2Seq
|
@@ -127,4 +131,4 @@ The license on this model does not constitute legal advice. We are not responsib
|
|
127 |
|
128 |
@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
|
129 |
|
130 |
-
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
|
|
|
6 |
## Model Details
|
7 |
|
8 |
This model is an int4 model with group_size 128 and symmetric quantization of [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round). Load the model with revision="e289950" to use AutoGPTQ format.
|
9 |
+
|
10 |
+
auto-round>0.51
|
11 |
+
|
12 |
+
transformers>=4.52.0
|
13 |
+
|
14 |
## How To Use
|
15 |
### INT4 Inference
|
16 |
|
17 |
```python
|
|
|
18 |
import torch
|
19 |
from PIL import Image
|
20 |
from transformers import AutoProcessor, AutoModelForVision2Seq
|
|
|
131 |
|
132 |
@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
|
133 |
|
134 |
+
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
|