LangChain tutorial: fine-tuning and evaluating LLaMA2-7b-chat and gpt-3.5-turbo with LangSmith
Original title:Using LangSmith to Support Fine-tuning
AI summary
LangChain released a fine-tuning and evaluation guide that uses LangSmith for dataset management and evaluation, fine-tunes LLaMA2-7b-chat with qLoRA on CoLab, and fine-tunes OpenAI's gpt-3.5-turbo with 50 samples, with knowledge graph triple extraction as the test task.
Key Takeaways
- LangChain released a fine-tuning and evaluation guide that uses LangSmith for dataset management…
- fine-tunes LLaMA2-7b-chat with qLoRA on CoLab,and fine-tunes OpenAI's gpt-3.
- 5-turbo with 50 samples,with knowledge graph triple extraction as the test task.
Quick Facts
- Published
- Updated
- Source
- LangChain:Blog(RSS)
- Category
- Tutorials & Tips
- AI score
- 60
原文给出了从数据集管理到评测的完整微调流程和实测分数,读者可以据此判断小模型微调与 GPT-4 few-shot 的取舍。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: LangChain tutorial: fine-tuning and evaluating LLaMA2-7b-chat and gpt-3.5-turbo with LangSmith. August 23, 2023. https://new.nat6.net/en/news/cmt96t9tm0aucroly7tsytvkz/