Comments (1)
BlinkDL
commented on May 8, 2024
1
RWKV 14B: 3 months for 332G tokens on 8x8=64 A100-40Gs. DeepSpeed ZERO2 + CP. Note I was using very small bsz (8x8x2=128, seems good for slightly better model performance) and it could be 50% faster if you use larger bsz.
from rwkv-lm.
Related Issues (20)
- Gratitude and Inquiries HOT 1
- Exception has occurred: IndexError HOT 1
- Training on Cuda version 11.2, 11.3 HOT 1
- 运行报错 HOT 3
- lora训练时出错 HOT 3
- 如何训练rwkv-5-0.1b，显示权重加载错误 HOT 1
- 想问一下能否提供一个CHN+JPNTuned的7B版本 HOT 1
- AttributeError: 'MyDataset' object has no attribute 'global_rank' HOT 3
- 出错 No such file or directory: 'cuda/wkv_op.cpp' HOT 1
- 可以给个requirements？ HOT 4
- huggingface无法使用 HOT 1
- Got ImportError when using load() to load wkv_cuda HOT 1
- 如何将rwkv或者retnet用于ocr任务？ HOT 1
- v5 train error HOT 2
- size mismatch for blocks.11.ffn.value.weight: copying a param with shape HOT 3
- v5 train error HOT 1
- 请教一下，训练RWKV-4-Pile-3B-20221008-8023，提示错误 HOT 3
- how to pretrain v5 other lang? HOT 3
- 训练RWKV-4，报错 HOT 1
- MoE support HOT 1
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 rwkv-lm.