-
If the self-attention containes some bias, e.g. (Q*K+bias_1+bias_2)*V, can we still aplly YOSO or Nystromformer to speed up the computation? If we can still do it, can you give me some hit on how to d…
-
# Transformer 在视觉方面的应用
## Reference
- 2021-01 A Survey on Visual Transformer [[Paper](https://arxiv.org/pdf/2012.12556.pdf)] [[Note](https://github.com/junxnone/tech-io/issues/926)]
- 2021-01 Tr…
-
### Feature request
I encountered a KeyError while loading the phi3-v vision model into Optimum Huggingface. The error message states:
```
KeyError: 'phi3-v model type is not supported yet in Nor…
-
Congrats on your great work!
I am verifying your method on vision tasks and have a small concern on the influence of the "conv_kernel_size" of the 2D group-convolution in your task and I find that …
-
I run the program in pycharm, one error listed below occurs, how to solve it?
ValueError: Unrecognized model in weights/icon_caption_florence. Should have a `model_type` key in its config.json, or co…
-
### Model description
Do we support Model2Vec embedding models?
E.g: https://huggingface.co/minishlab/potion-base-8M
https://minishlab.github.io/tokenlearn_blogpost/
### Open source status
- […
-
For models with only Decoder-stacks, how to apply causal mask?
-
This is great! Anyway I can help out? Are you all doing this for school or part of a lab?
-
像是缺失了文件
Unrecognized model in D:\LIUGEGE\ComfyUI\models\Joy_caption_alpha\text_model. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: albert, a…
-
This issue is linked to the [ONNXConfig for all](https://huggingface.co/OWG) working group created for implementing an ONNXConfig for all available models. Let's extend our work and try to add all mod…