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
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
🧩DemoGPT (@demo_gpt) / X
Thread by @LangChainAI on Thread Reader App – Thread Reader App
Thread by @RLanceMartin on Thread Reader App – Thread Reader App
🧩DemoGPT (@demo_gpt) / X
Nicolas A. Duerr on LinkedIn: #business #strategy #partnerships
Multi-Vector Retriever for RAG on tables, text, and images 和訳｜p
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: #business #strategy #partnerships
Multi-Vector Retriever for RAG on tables, text, and images 和訳｜p
컴퓨터 vs 책: [B급 프로그래머] 8월 4주 소식(빅데이터/인공지능, 하드웨어, 읽을거리 부문)
Thread by @LangChainAI on Thread Reader App – Thread Reader App
Thread by @RLanceMartin on Thread Reader App – Thread Reader App
Applying OpenAI's RAG Strategies 和訳｜p
Nicolas A. Duerr on LinkedIn: #futurebrains #platform #marketplace #strategy #innovation
