The future is #finetuned! You can get the same performance at a fraction of the cost by fine-tuning open-source #LLMs compared to commercial models like #GPT4. If you're at @AIDevWorld don't miss our talk with @devvret_rishi
. https://
pbase.ai/3FupZd6 #AIDevWorld
LLMS
-
Fine-tuning Open-Source LLMs: Cost-Effective Alternative to GPT-4
By
–
-
LangChain CEO Launches Functions Tools Agents Course
By
–
Announcing LangChain CEO @hwchase17’s new short course, Functions, Tools, and Agents with LangChain! Covers latest LLM function calling, how to use LLMs to process formatted data (such as JSON) to integrate with other software, and building agents. https://t.co/W0PwiYheDL pic.twitter.com/pC61FRf2aZ
— Andrew Ng (@AndrewYNg) 25 octobre 2023Announcing LangChain CEO @hwchase17
’s new short course, Functions, Tools, and Agents with LangChain! Covers latest LLM function calling, how to use LLMs to process formatted data (such as JSON) to integrate with other software, and building agents. https://
deeplearning.ai/short-courses/
functions-tools-agents-langchain
… -
Search LLM API Integration: Current Availability and Options
By
–
Is there a Google/Bing Search + LLM available as an API today to try? * @perplexity_ai is the best here, but their search+LLM not yet available as an API
* Bard APIs are not openly available yet (need to do some data processing asap) -
Distributed Training and Efficient Finetuning Guide
By
–
Everything about Distributed Training and Efficient Finetuning | Sumanth's Personal Website https://
bit.ly/3tDPqpS #AI #MachineLearning #DeepLearning #LLMs #DataScience -
What Algorithms Can Transformers Learn Study
By
–
What Algorithms can Transformers Learn? A Study in Length Generalization Zhou et al.: https://
arxiv.org/abs/2310.16028 #ArtificialIntelligence #DeepLearning #MachineLearning -
LLM Transparency: Disclosure Builds User Trust and Clarity
By
–
Thanks. When it responds using the “I” pronoun, however, as most LLMs do when you ask the question, “are you real?” users get confused as to who (designers or a non sentient AI being portrayed as sentient) they’re speaking to. My reco is upfront disclosure to build trust.
-
Building Open-Source RAG ChatGPT Web App
By
–
Good morning fellow AI enthusiast! This week's iteration focuses on how we built an open-source RAG-based ChatGPT Web App. We dive into how to leverage the best models like ChatGPT, and the challenges (and tips) building RAG-based apps! Read more: https://
open.substack.com/pub/louisbouch
ard/p/meet-our-new-ai-tutor?r=25qlky&utm_campaign=post&utm_medium=web
… -
Open-Source RAG ChatGPT Web App AI Tutor Launch
By
–
How we Built an Open-Source RAG-based ChatGPT Web App: Meet Our new AI Tutor! This is Towards AI's new AI tutor, a question-answering chatbot built to answer anything about LLMs with up-to-date information! (work in progress, please try it and give us feedback, its free!) Learn
-
Apple’s LLM OS Strategy and Siri Automation Capabilities
By
–
Been thinking about Apple’s unique position with an LLM OS. Many don’t realize that iOS and macOS already have extremely detailed automation tools compared to other OSes. Shortcuts, Automator, AppleScript, their accessibility tools… So Siri already has the pathways it needs to
-
MLOpsWorld Austin: BERT vs GPT4 Talk and Baggage Issues
By
–
Just got to @MLOpsWorld in Austin! Looking forward to my talk tomorrow at 14:00 (“How many labelled examples do you need to beat GPT4 with BERT?”) Unfortunately the airline gate-checked our bags in Berlin and didn’t put them onto our connection to Austin . So we arrived with