-
Hello, thank you for sharing the source code. While trying to reproduce **SST2 task result with RoBERTa-base model**, I've encountered some questions regarding the hyper-parameters, lora_alpha, and a …
-
We need to research on what sort of analytics we can do in terms of tagging context, credibility of a source etc.
-
I have the following error when finetune the DocOwl1.5-Omni. It always raises error when index is 10. Please help!!!
```
File "/opt/conda/envs/mplug_owl2/lib/python3.10/site-packages/deepspeed/run…
-
Time Series Classification is a very popular machine learning problem.
You can find a full survey and empirical study ([link to paper](https://link.springer.com/article/10.1007/s10618-016-0483-9)) o…
-
Hi,
Great work. Thanks for building this library. I am working on a life-long learning problem that tends to have a large number of data points, and thus a large kernel matrix.
It appears tha…
-
## What/Why
### What are you proposing?
We want to be able to build against the OpenSearch CI system the same way as any other plugin in the opensearch-project repo. The first step is just to build …
-
**Aim**
Find out what self-attention actually does (ie. benefits, limitations) and what research is already out there.
**Plan**
- [x] [Low-Rank and Locality Constrained Self-Attention for Sequence Mo…
-
The training does not start..my memory is completely occupied but GPU is at 0%.
Screenshot attached below. Pls help .
![image](https://github.com/X-PLUG/mPLUG-DocOwl/assets/74967139/a587f57a-8694-…
-
In terms of UI, the change should be to replace the red part here:
![screenshot 2019-02-27 at 13 22 23](https://user-images.githubusercontent.com/18445/53490996-793ba180-3a95-11e9-83f1-843fa0afcd65…
-
I'm trying to use DeepSpeed-Chat stage2 scripts to do rlhf with Qwen1.8b-chat model,I change some parts in dschat and main.py to load my model, the most different part is:
```
if 'Qwen' in model_nam…