-
### What happened?
![微信截图_20240826183956](https://github.com/user-attachments/assets/05daea40-7b8f-4f69-81c0-10813fb8d3b5)
Error occurred when executing KSampler (Efficient):
Inference tens…
-
# 🌟 New model addition
My teammates and I (including @ice-americano) would like to use efficient self attention methods such as Linformer, Performer and Nystromformer
## Model description
The…
-
Hi! I'm tried to finetune llama-2-13b with bottleneck Adapter, but it got a ValueError that cannot finetune the model loading by using load_in8bit. What is the problem? How can I solve it?
**ValueE…
-
Hi there -- I took a quick look at your code. A key motivation for modeling sequences via linear recurrence relations (instead of, say, self-attention) is that they can be implemented to execute with …
-
### Describe the issue
com.microsoft::BeamSearch op is outputting wrong values when following conditions are satisfied:
- Running on CUDA execution provider
- Using _model_type_ = 1 (T5-like mode…
-
### Expected Behavior
i can load flux model yesterday, but i don't know why there the error occur today.
### Actual Behavior
please check the coding
### Steps to Reproduce
it's not about the work…
-
Provided code calculates matrix product of q and k.
https://github.com/YuchuanTian/DiJiang/blob/main/modeling/pythia-2.8B-dijiang/modeling_gpt_neox_dijiang.py#L286
That means it has computational …
-
I refined llama3.1 8b bnb 4bits according to your recommendations with my own train+eval dataset and saved as merged 16 bits. I now want to create an inference by loading the 16b merged model and usin…
-
ENVIRONMENT
Windows 10
GPU 1660 Super
32 gb ram
So i tried a lora model that i made, and i try to get results from prompts but i get an warning lora keys not loaded and the image is not the de…
-
Hi Phil, thanks for the great repo.
I compared your implementation of ViT with huggingface's (https://github.com/huggingface/transformers/blob/master/src/transformers/models/vit/modeling_vit.py) and…