Comments (1)
As we don't have the huge resources for launching the fully release tests. Let's setup a specification to standardize the processes, like, distributing the release testing tasks to the authors and collecting them, finally generating the release tests report.
For an instance:
- Selecting the volunteers from authors, AUTHOR1, AUTHOR2, AUTHOR3.
- Distributing the release tasks to the 3 authors.
- Iterating the candidate versions once we found any issue.
- Generating the release report.
And more, the all processes should be tracked in a Github issue.
from openrlhf.
Related Issues (20)
- Strange Kill of Critic Model HOT 5
- 使用Deepseek-lite训练DPO,显示expected mat1 and mat2 to have the same type, but got: float != c10: : BFLoat16 HOT 3
- Will 2 x GPU setups be supported HOT 1
- Dummy token for prompts in HH datasets HOT 2
- Does this codebase consider using "torch.compile"? HOT 2
- wrong action_log_probs returned? HOT 1
- 可以增加支持SimPO吗
- zero3 training error HOT 1
- Failed to update weights to vLLM HOT 3
- run train_ppo_llama_ray.sh error
- Moving model between GPU and CPU HOT 3
- train_ppo_llama_ray_70b.sh run two H800 machine error HOT 1
- ray多节点训练下deepspeed zero3的切分还是按照 node数*8卡来切分吗? HOT 1
- train_ppo_llama_ray.sh run two H800 machine error HOT 3
- mixtral 8*7B的最佳训练参数,推理参数可以提供一个吗? HOT 1
- [Question] Is multi-nodes stage 3 model loading supported? HOT 2
- 训练启动时,如何指定gpu的数量? HOT 1
- /openrlhf must be an existing directory or a zip package HOT 1
- 多卡并行无法model.generate HOT 2
- Generate function for distributional training 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 openrlhf.