“14. Scale often has surprising emergent properties.” Amen, both in language models and humans
LLMS
-
Ludwig v0.9 Released: Zero-Shot LLM Inference and Fine-Tuning
By
–
Announcing Ludwig v0.9 Zero-shot inference w/ LudwigModel.generate endpoint for LLMs Adapter-based fine-tuning w/ #LLM encoders for text classification New LLM architectures like Mistral/Zephyr, Phi-1/1.5/2, #Mixtral and more! https://
pbase.ai/4ayPvfM -
Mistral-Medium Now Available on Poe Platform
By
–
Try Mistral-Medium at https://
poe.com/Mistral-Medium or via the Poe apps on all platforms! (2/2) -
Mistral-Medium Now Available on Poe Platform
By
–
Mistral-Medium is now available on Poe! This is Mistral AI’s largest and most powerful model, performing better than Mixtral-8x7b and Mistral-7b on benchmarks across the board. (1/2)
-
AI Companies’ True Priorities Revealed Through Their Evaluation Choices
By
–
If you want to know what an AI company truly cares about, just look at what evals they run. – Lots of academic evaluations against GPT-4 means pressure to train a model more capable than OpenAI.
– Companies that actually care about their consumer product will probably run lots -
Crew AI: Multi-Agent Framework for Building AI Teams
By
–
Crew AI is a multi-agent framework built on top of LangChain
— LangChain (@LangChain) 21 décembre 2023
We're publishing a blog from its creator @joaomdmoura explaining how it works
Check it out here – and go build some awesome stuff with it!
Blog: https://t.co/OEancB8d6a https://t.co/IfYdUww52T pic.twitter.com/wyusg3YgUNCrew AI is a multi-agent framework built on top of LangChain We're publishing a blog from its creator @joaomdmoura explaining how it works Check it out here – and go build some awesome stuff with it! Blog: https://
blog.langchain.dev/crewai-unleash
ed-future-of-ai-agent-teams/
… -
Paper Reports Non-Deterministic Logprobs from OAI API Despite Seed Parameter
By
–
Update: But not for logprobs. Paper published today by @maksym_andr reports logprobs returned from OAI API are non-deterministic even with the seed parameter. Not sure how to reconcile this with sampled completions described as deterministic.
-
Free RAG Course from Gen AI 360 Foundational Model Certification
By
–
Jump on our free RAG course from the Gen AI 360 Foundational Model Certification (Built in collaboration with @activeloop
, @towards_AI
, and the Intel Disruptor Initiative): https://
learn.activeloop.ai/courses/rag -
LangChain vs LlamaIndex vs OpenAI GPTs Comparison Guide
By
–
New video! @langchain vs. @llama_index vs. @OpenAI GPTs: Which one should you use? https://
youtu.be/g84uWgVXVYg