Training foundation models require enormous resources. We can overcome this by working with the vast collective intelligence of existing models. @HuggingFace has over 500k models in dozens of modalities that, in principle, can be combined to form new models with new capabilities!
OPEN SOURCE
-
Evolutionary Model Merge: Automating Foundation Model Development
By
–
Introducing Evolutionary Model Merge: A new approach bringing us closer to automating foundation model development. We use evolution to find great ways of combining open-source models, building new powerful foundation models with user-specified abilities!https://t.co/G0EyM7pztr pic.twitter.com/msOokvqGbR
— Sakana AI (@SakanaAILabs) 21 mars 2024Introducing Evolutionary Model Merge: A new approach bringing us closer to automating foundation model development. We use evolution to find great ways of combining open-source models, building new powerful foundation models with user-specified abilities! https://
sakana.ai/evolutionary-m
odel-merge/
… -

Vector Search for Practitioners: Elastic Toolkit for NLP Solutions
By
–
Vector Search for Practitioners with Elastic — A toolkit for building #NLProc solutions for search, observability, and security: http://
amzn.to/3vEkWFe via @PacktPublishing ——
#DataScience #Analytics #DataScientists #MahineLearning #BigData #AI #VectorDB #RAG #LLMs #GenerativeAI -
AI Chip Market Growth: Open-Source Solutions Drive Adaptability
By
–
#AI is evolving rapidly. With the global #chip market set to hit $588B in 2024 and its pool of players only growing, choosing the right solution is crucial. #UAI CEO Chris Walker says "prioritize open-source for one reason: adaptability." (via @Inc
) -
Bay Area Event: Open-Source LLM Frameworks and Production Apps
By
–
Bay Area Friends: Join us Apr 4th to learn about the lastest open-source #LLM frameworks and tips for building #production-grade apps from the leaders at @predibase @llama_index
, @tryolabs and @guardrails_ai
! Save your spot and invite your friends! https://
pbase.ai/4am4ys9 -
LangGraph Quickstarts: Easier Multi-Agent App Development
By
–
New LangGraph Quickstarts We've made it easier to get started building multi-agent apps with LangGraph and LangGraph.js with revamped quickstarts! Try them out, and let us know what you think! And stay tuned – we have a lot of exciting things coming around LangGraph.
-
claude-prompt-engineer: AI Agent Creates Optimal Claude Prompts
By
–
Introducing `claude-prompt-engineer` ✍️
— Matt Shumer (@mattshumer_) 20 mars 2024
An agent that creates optimal Claude 3 prompts.
Just describe a task, and a chain of AIs will:
– Generate many possible prompts
– Test them in a ranked tournament
– Return the best one
And it's open-source: https://t.co/nrivU2BWmn pic.twitter.com/ruxDCrq1DLIntroducing `claude-prompt-engineer` An agent that creates optimal Claude 3 prompts. Just describe a task, and a chain of AIs will:
– Generate many possible prompts
– Test them in a ranked tournament
– Return the best one And it's open-source: https://
github.com/mshumer/gpt-pr
ompt-engineer
… -
Developer Creates Advanced AI System With Math Problem Solving
By
–
It's actually wild; today it solved a very complex math problem for me, and I was like, did I just create AGI by accident? Lol I am planning to add more features like file retrieval, vision, etc. Stay tuned. I am also running a company so I’ll do my best! Haha
-
MLX Framework Integration with Teknium’s New Model
By
–
I actually think I could probably spin this for MLX, especially with the new @teknium model!
