Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update README.MD #2

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update README.MD #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions README.MD
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,11 +126,11 @@ python evaluate.py \

The examples generated by [LongQLoRA-Vicuna-13b-8k](https://huggingface.co/YeungNLP/LongQLoRA-Vicuna-13b-8k) ars as follows.

Examples of long context generartion, the input context lengths are between 4096 and 8192 which are larger than original context length of LLaMA2.
Examples of long context generation, the input context lengths are between 4096 and 8192 which are larger than original context length of LLaMA2.

<img src="figure/longdemo.png" width="800">

Examples of short context generartion, model keep the performance of short instruction following.
Examples of short context generation, model keep the performance of short instruction following.

<img src="figure/shortdemo.png" width="800">

Expand All @@ -150,4 +150,4 @@ Examples of short context generartion, model keep the performance of short instr
## Acknowledgement
- This work combines the advantages of [QLoRA](https://github.com/artidoro/qlora), [Position Interpolation](https://arxiv.org/abs/2306.15595) and [LongLoRA](https://github.com/dvlab-research/LongLoRA)
- The code of Shift Short Attention is implemented by [LongLoRA](https://github.com/dvlab-research/LongLoRA)
- The training code is modified upon [Firefly](https://github.com/yangjianxin1/Firefly)
- The training code is modified upon [Firefly](https://github.com/yangjianxin1/Firefly)