Comments (3)
您好,感谢您的关注。
我们的预训练代码目前仅支持Decoder-Only的架构,比如Llama系列等,这种架构的预训练步骤可以参考此处的readme。
然后是您提到的那个链接,根据config.json,这是一个BART模型,是一个Encoder-Decoder架构,我们目前的代码并不直接支持这一点,但是理论上来说,只要更改数据输入的部分即可快速的适应Encoder-Decoder架构的训练。如果您实现了这一点,欢迎提交PR。
如果您还有其他问题,请告知我 :)
from knowlm.
@MikeDean2367 谢谢您的解答。我现在的功力还不会自己训练。我先试试您说的README里的步骤吧。再次感谢你们慷慨的开源贡献!
from knowlm.
您后续如果有任何问题欢迎随时提问
from knowlm.
Related Issues (20)
- 请问何时开源7b的zhixi大模型 HOT 1
- 关于knowLM的使用 HOT 7
- 环境配置 HOT 5
- 模型量化 HOT 8
- 请教KnowLM、IEPile和DeepKE-LLM三者之间的关系 HOT 3
- 模型评估 HOT 7
- 请问一下lora指令微调knowlm可以用中文数据集吗?我用中文的会报错,改成英文就不会 HOT 4
- 是否有Dialogue Model这类信息抽取模型在常用IE数据集上的评测结果,如准确率,F1呢 HOT 2
- 大规模数据读取费时 HOT 2
- 关于Lora指令微调权重获取与复原,这一部分的链接好像有问题,https://github.com/zjunlp/KnowLM/tree/main#22-%E9%A2%84%E8%AE%AD%E7%BB%83%E6%A8%A1%E5%9E%8B%E6%9D%83%E9%87%8D%E8%8E%B7%E5%8F%96%E4%B8%8E%E6%81%A2%E5%A4%8D HOT 7
- 实体在Wikidata中对应的ID HOT 1
- 二次训练 HOT 4
- 您好,我想在自己的数据集上对经过llama.cpp量化的zhixi大模型进行评估,我应该怎么做,能否给出一些指导,非常感谢您的帮助。 HOT 4
- 评价指标Rouge HOT 2
- 下载zip解压,按步骤操作,报OSError HOT 3
- 求助:由于在国内使用阿里云服务器,无法科学上网接入huggingface下载模型,通过魔塔下载好模型后运行,代码有报错 HOT 5
- generate_lora_web.py报错求助 HOT 5
- 训练数据集 HOT 4
- 模型加载 HOT 8
- 环境配置pip下载不成功 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 knowlm.