Comments (3)
mabaochang
commented on September 13, 2024
3
感谢评估，目前开源的模型还比较早期，后续我们也会在指令理解安全性上持续迭代，期待能release 更多更好的模型回馈社区
from belle.
TestNLP
commented on September 13, 2024
感谢评估，目前开源的模型还比较早期，后续我们也会在指令理解安全性上持续迭代，期待能release 更多更好的模型回馈社区
模型进一步训练的话，需要多少卡？能把你们训练的资源列出来吗？
from belle.
mabaochang
commented on September 13, 2024
我们后续会把实验的更多细节列出来的
from belle.
Related Issues (20)
- 输出多个结果 HOT 1
- how did you get category about dataset train_3.5M_CN_With_Category? HOT 1
- 使用run_pt.sh进行lora的非指令微调，没有效果。
- 【模型训练】我想请问模型输出的文件应该怎么看，每个文件都是什么作用呢？
- 【模型多轮对话推理】想请问多轮对话推理时，上下文如何拼接送入模型 HOT 1
- 12块8G显存可以用来训练吗
- What's the correct form of prompt in the scenario of multi-turn conversations HOT 2
- 预训练报错 NCCL Socket Timeout HOT 2
- 作者能否给一套最新代码适配的requirement.txt呢？ HOT 1
- 13类数据聚类或分类的方法 HOT 1
- 如何训练vl模型 HOT 4
- VL模型效果非常差 HOT 10
- 哪里可以找到VL模型的权重 HOT 3
- provide BELLE-VL tech report ? HOT 3
- deepspeed warmup_num_steps:"Auto" 报错 HOT 3
- Is there any prompt examples of using BELEE for persona-based dialogue generation?
- 请问：论文中预训练采用的MIP训练方式的效果，大家在其他领域有验证过效果吗？ HOT 1
- BELLE/train/src/models/generation_utils.py这个文件不是只有transformers<=4.30.2时使用自定义的trainer.py才会触发吗？但里面generation_utils.py为啥有4.30.2版本以上的东西，训练报错：ImportError: cannot import name 'SequenceBiasLogitsProcessor' from 'transformers.generation.logits_process'
- 微信二维码已过期 HOT 1
- 请问Chathome中，提到的数据比例1:5，指的是token数量1比5，还是数据条数1比5？ 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 belle.