Devs, check out the tutorial @mervinpraison
— Groq Inc (@GroqInc) 21 avril 2024
has made with Llama3 from @AIatMeta https://t.co/LgiwsYC9pA
Devs, check out the tutorial @mervinpraison has made with Llama3 from @AIatMeta
GENERATIVE AI
-
Developers Check Out Llama3 Tutorial by Mervin Praison
By
–
-
Build Serverless AI Chat RAG LangChain.js Azure
By
–
Build a serverless AI chat with RAG using LangChain.js This shows how LangChain.js, Ollama with Mistral 7B model and Azure can be used together to build a serverless chatbot that can answer questions using a RAG pipeline https://
techcommunity.microsoft.com/t5/apps-on-azu
re-blog/build-a-serverless-ai-chat-with-rag-using-langchain-js/ba-p/4111041
… -
Understanding LLM Hallucinations: Critical Challenge for Reliable AI Tools
By
–
The biggest challenge IMO is helping people understand the hallucination problem and how unreliable these tools are – if you don't understand that it's much harder to put these things to good use
-
Making Unreliable AI Algorithms Work Practically
By
–
We can also figure out how to get useful results out of inherently unreliable algorithms – it's definitely possible, I've been finding useful ways to put this stuff to work for a couple of years now
-
LLM Non-determinism and Endpoint Predictability Challenges
By
–
The amount of non-deterministic behavior LLMs introduce makes me believe in techno-sorcery futures. Let's chant a verse, burn candles, perform data prayers and result purification rituals. Anything to get this endpoints perform predictable across different input
-
AI Autonomously Generates and Tests Hypotheses
By
–
It generates hypotheses autonomously and tests them autonomously
-
Grok AI Auto-Generated Summary Review and Analysis
By
–
I like the Grok @X auto-generated summary.
I previously wrote a more in-depth review at Ground Truths (see profile) -
GPT-2 Reproduction with Increased Channel Size and Memory Optimization
By
–
We want to do a full GPT-2 repro, at channel size 1600 this is 2.1X higher C. And we'll want to ~max out batch dim to fit in memory too. So the "easy times" will be over soon.
