Blog | Making the right characters for [insert anything] https://
bit.ly/3NioC5I
#AI #MachineLearning #DeepLearning #LLMs #DataScience
LLMS
-

Creating the Right Characters for AI Applications
By
–
-
LLMs as Scaffolding for Advanced AI Systems
By
–
Hot take: LLM based AI is a scaffolding stage for the truly powerful AI that will be able to directly tap into the economically viable technology of its own.
-

Open Source AI Models Overtaking Proprietary Solutions
By
–
Open source AI models are on a path to overtake proprietary models.
-
Committing to Single LLM as Primary AI Assistant Tool
By
–
My take is that for the upcoming days, I am going to make this my only LLM, essentially replacing everything I use GPTs with this. Then, I will have a better view. Until then, so far, I am pretty impressed. This is the first time I felt I can actually fully commit to that.
-
Zephyr 3B Enhances SDXL Prompt Generation Efficiently
By
–
Great work on Zephyr 3B by the way. I have been using it to improve my SDXL prompts, and it's amazing. For that size, it sure packs a punch!
-

Fine-tuning Open-Source LLMs Talk at AI.dev Conference
By
–
Headed to http://
Dev.AI world? Catch this talk on fine-tuning smaller task specific open-source #LLMs w/ @devvret_rishi
, Cofounder / CEO @predibase (it's streamed for free!) #AIdotDev • Talk details: https://
aidevcass23.sched.com/event/1VUUQ?if
rame=no
…
• Live stream: https://
youtube.com/watch?v=IOr1XL
uEQTM
… -

LLMs Graph Reasoning: Optimal Encoder Selection at NeurIPS
By
–
Graphs are invaluable for representing & analyzing complex relationships. Drop by the #NeurIPS2023 Google booth at 4pm today to hear @phanein
, @BahareFatemi
, & Jonathan Halcrow talk about the correct choice of encoders to boost performance on graph reasoning tasks using LLMs. -

Extracting Training Data from ChatGPT Analysis
By
–
Extracting Training Data from ChatGPT https://
not-just-memorization.github.io/extracting-tra
ining-data-from-chatgpt.html
…
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Mistral 7B RAG Production Deployment with LangServe
By
–
Deploying Mistral-7B RAG to Production Join our friends at @AIMakerspace to learn how to go from prototype to production with LangServe and Mistral 7B! Will cover LCEL, HuggingFace, LangServe, LangSmith This Thursday, 10am PST Link:
-
Learning Qdrant Vector Database Integration with LangChain
By
–
If you want to learn how to use @qdrant_engine with LangChain, check out this session with @LukawskiKacper
!