Comments (3)
没有测过不同版本的flash-attn欸,不过我觉得这个影响不大,直接测开源的model结果是否接近呢?训练数据和超参有没有区别嘞?其他benchmark的结果差的多吗?
from ask-anything.
我这边查看了代码,你们训练确实使用的是v2版本的flash_attn,麻烦确认下具体是哪个版本的flash_attn
from ask-anything.
flash-attn 2.1.1
from ask-anything.
Related Issues (20)
- 一二阶段训练数据读入问题 HOT 1
- Question about training stage3 in videochat2 HOT 3
- Warnings in loading the models HOT 1
- The final fine-tuned vision encoder HOT 1
- Any instructions for fine-tuning on custom datasets? HOT 1
- stage1无法eval HOT 1
- 第一个step后第三阶段loss变为nan HOT 3
- MVBench local evaluation HOT 4
- Question about the output scores in videochat2
- Question about attention mask
- 您好,急问为什么执行inference demo时,对一定数量的视频生成caption之后程序就会卡死
- Disk Space, GPU Usage, and Training Duration for Stage3
- Hardware configuration conditions? HOT 1
- 'Dataset' object has no attribute 'components' HOT 2
- SH-IDC1-10-140-1-1, 10068 | cannot be retrieved HOT 1
- Is there a bug in mvbench.ipynb check_ans
- typo: assert -> asset for folder name
- clevr数据集的使用 HOT 15
- How to implement VideoChat2_text HOT 1
- hola queremos follar HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ask-anything.