CODE - AI Dynamics

Fifth Video: Optimal LLM Training and Fine-Tuning Techniques

By

–

01 December 2023 14h10

Good morning fellow AI enthusiast! This is the fifth iteration of my video series for our free course "Training & Fine-Tuning LLMs for Production"! In this one, we dive into the world of large language models (LLMs) and discover the optimal techniques for your specific tasks!

→ View original post on X — @whats_ai

1 December 2023

TaskWeaver: Code-First Agent Framework for AI Automation

By

@montreal_ai

–

30 November 2023 23h42

TaskWeaver: A Code-First Agent Framework Qiao et al.: https://
arxiv.org/abs/2311.17541 #ArtificialIntelligence #ChatGPT #DeepLearning

→ View original post on X — @montreal_ai

30 November 2023

best_of persists for gpt-3.5-turbo-instruct in Completion API

By

@goodside

–

30 November 2023 20h46

best_of still exists in the API for gpt-3.5-turbo-instruct, which will be the only model using the Completion API (which also returns top-5 logprobs) once all legacy completion models are shut off on Jan 4, 2024.

→ View original post on X — @goodside

30 November 2023

PyTorch LLM Inference Optimization Beats Industry Standards

By

@soumithchintala

–

30 November 2023 19h46

using simple pytorch code and advanced features, you get LLM Inference speeds that beat most LLM Inference engines out there. Checkout this great post and work from @cHHillee

→ View original post on X — @soumithchintala

30 November 2023

New Template Redacts Information Before LLM Processing

By

@langchain

–

30 November 2023 19h43

Check out this new template that redacts information before processing it with the LLM!

→ View original post on X — @langchain

30 November 2023

Deconstructing RAG: Popular Concepts and Implementation Guide

By

@langchain

–

30 November 2023 17h56

Deconstructing RAG Given the importance of RAG and the fast pace of development, we've grouped popular RAG concepts into a few categories and created guides for each one. The this new blog post, we summarize these categories / guides and highlight some questions to ask

→ View original post on X — @langchain

30 November 2023

OpenAI releases Deno SDK for JavaScript developers

By

@officiallogank

–

30 November 2023 17h55

And… we’re back to shipping! Announcing the @OpenAI Deno SDK, now available at https://
github.com/openai/openai-
deno-build
…, built in collaboration with @stainlessapi
. Deno is a Javascript runtime that natively supports Typescript, is secure by default, and provides an awesome DevX.

→ View original post on X — @officiallogank

30 November 2023

Deploy LangChain Templates on Google Cloud Run

By

@langchain

–

30 November 2023 17h43

Deploy LangChain on Google with LangServe A big focus over the past month has been developing production ready, easy to customize LangChain templates for a variety of use cases We collaborated with Google to show how to deploy them on Cloud Run

→ View original post on X — @langchain

30 November 2023

Advanced Lane Detection with SegFormer Model Fine-tuning

By

@learnopencv

–

30 November 2023 13h55

🚗🤖 Dive into the world of Autonomous Vehicles with us!https://t.co/cGlqh8iSz7

🛣️ In our latest video, we're all about Advanced Lane Detection. 🚀

Join us as we fine-tune the SegFormer model by Hugging Face using Google Colab to supercharge those lane detection skills!… pic.twitter.com/UXzvaSF5CK
— Satya Mallick (@LearnOpenCV) 30 novembre 2023

Dive into the world of Autonomous Vehicles with us! https://
youtube.com/watch?v=awiQKQ
d3gE4
… In our latest video, we're all about Advanced Lane Detection. Join us as we fine-tune the SegFormer model by Hugging Face using Google Colab to supercharge those lane detection skills!

→ View original post on X — @learnopencv

30 November 2023