n1ck-guo commited on
Commit
f56d52a
·
1 Parent(s): b0c2223

update to transfomers 4.52

Browse files

Signed-off-by: n1ck-guo <[email protected]>

Files changed (1) hide show
  1. README.md +6 -2
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)