-
### Feature request
Implement this in Paddle paddle
Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this fi…
-
### Model/Pipeline/Scheduler description
Yesterday Kwai-Kolors published their new model named **Kolors**, which uses unet as backbone and ChatGLM3 as text encoder.
Kolors is a large-scale text-…
-
**Describe the bug**
deepspeed-zero3,lora_target_modules ALL,model_type phi3-vision-128k-instruct,多机多卡,在resume from checkpoint的时候,模型似乎无法加载。需要注意的是,此时的chekpoint文件夹内只包括lora相关的参数,但是报错显示模型在加载更多参数。
> Fi…
-
### Describe the bug
I found Pixart-Sigma is incompatible with mixed precision inference, loading models both in `float32` and in `float16` have similar problem.
I guess this problem may have some…
-
python: 3.9.19
torch:1.12.1
marker-pdf: 0.2.13
code : python convert.py doc_dir ouput
error info:
Traceback (most recent call last):
File "/root/marker/convert.py", line 135, in
m…
-
Hi! I'm interested in using the rotary embeddings with `x_pos=True` so my transformer is length-extrapolable. However, I noticed the readme mentions this technique works only with autoregressive trans…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
Tried to run SDXL. Downloaded models
First it didn…
-
It would be convenient to allow the encoder [output_size](https://github.com/CUNY-CL/yoyodyne/blob/master/yoyodyne/models/modules/lstm.py#L99) to be different from the TransformerDecoder embedding siz…
-
I want to train the musicgen model (instead musicgen melody model) for Audio-Prompted audio continuation/generation tasks. According to my interpretation of the code provided below, it appears that `…
-
when i try to export onnx model from fairseq, i encountered this error. plz help support this operator
```
Traceback (most recent call last):
File "/home/workspace/terminal_launching/pt2onnx.py",…