[MRG] [POC] using langchain to quickly POC training and eval steps

MLSysOps / MLE-agent

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Ollama, etc supported. :fireworks: Code RAG

https://repx.app/

MIT License

1.03k stars 44 forks source link

[MRG] [POC] using langchain to quickly POC training and eval steps #10

Closed HuaizhengZhang closed 4 months ago

HuaizhengZhang commented 5 months ago

Closes #8

[x] understand stages
[x] data loading
[x] data engineering
[x] model selection (huggingface)
[x] model training (wandb)

future PRs
[ ] model evaluation (fairness, accuracy)
[ ] model deployment (streamlit)

Before submitting this PR, please make sure you have:

[x] confirmed all checks still pass OR confirm CI build passes.
[x] verified that any code or assets from external sources are properly credited in comments and/or in the credit file.

HuaizhengZhang commented 5 months ago

@huangyz0918 I will use langchain to quickly build several POCs and you can refactor them as you want

huangyz0918 commented 5 months ago

@huangyz0918 I will use langchain to quickly build several POCs and you can refactor them as you want

Ok, but I will not use langchain to build the system. PS. please rebase since your OpenAI key are uploaded in the git

huangyz0918 commented 5 months ago

I am working on using the openAI to load the data tonight, will refer to your poc code

HuaizhengZhang commented 4 months ago

@huangyz0918 merge first and will start to test and enhance your code