Using LangSmith to Support Fine-tuning
By A Mystery Man Writer
Description
Summary
We created a guide for fine-tuning and evaluating LLMs using LangSmith for dataset management and evaluation. We did this both with an open source LLM on CoLab and HuggingFace for model training, as well as OpenAI's new finetuning service. As a test case, we fine-tuned LLaMA2-7b-chat and gpt-3.5-turbo for an extraction task (knowledge graph triple extraction) using training data exported from LangSmith and also evaluated the results using LangSmith. The CoLab guide is here.
Context
I
Nicolas A. Duerr on LinkedIn: #business #strategy #partnerships
Multi-Vector Retriever for RAG on tables, text, and images 和訳|p
Thread by @RLanceMartin on Thread Reader App – Thread Reader App
Nicolas A. Duerr on LinkedIn: #business #strategy #partnerships
Nicolas A. Duerr on LinkedIn: #futurebrains #platform #marketplace #strategy #innovation
Using LangSmith to Support Fine-tuning
Thread by @RLanceMartin on Thread Reader App – Thread Reader App
大規模言語モデルとそのソフトウェア開発に向けた応用 - Speaker Deck
Week of 8/21] LangChain Release Notes
Multi-Vector Retriever for RAG on tables, text, and images 和訳|p
LangChain(0.0.340)官方文档十一:Agents之Agent Types_langchain agenttype-CSDN博客
LangChain on X: OpenAI just made finetuning as easy an API call But there's still plenty of hard parts - top of mind are *dataset curation* and *evaluation* We shipped an end-to-end
Nicolas A. Duerr on LinkedIn: #innovation #ai #artificialintelligence #business
Thread by @LangChainAI on Thread Reader App – Thread Reader App
Using LangSmith to Support Fine-tuning
from
per adult (price varies by group size)