Actually yeah I’m using sonnet more now
LLMS
-
Fine-tuning Models and Creating Llama 3 120B Instruct
By
–
My talk at @aiDotEngineer is starting soon! Come to Salon 8 to learn when to fine-tune models and how to create monstrosities like Llama 3 120B Instruct.
-
Latent Space Discord Community Continues LLM Paper Clubs During Conference
By
–
Even on @aidotengineer conf days, the @latentspacepod discord managed to keep up its unbroken stream of LLM paper clubs what absolute legends @eugeneyan @picocreator @ivanle @yoeven @honicky @YoungPhlo_ et al
-
GenAI Hallucinations: Why Models Fail Without Information
By
–
3. Hallucinations make GenAI applications unusable Models hallucinate because they are probabilistic. However, a model is much more likely to hallucinate when it doesn’t have access to the right information. Multiple studies have shown that hallucinations can be
-
Open LLM Leaderboard Insights and Model Rankings
By
–
maybe more insights here: https://
huggingface.co/spaces/open-ll
m-leaderboard/blog
… -
Model Merging Preserves Safety Alignment Better
By
–
Model Merging and Safety Alignment New paper looking into how model merging poorly preserves safety alignment. The authors modify EvoMM and LM-Cocktail to balance performance on safety data and domain-specific data. They show that this safety-aware merging approach can
-
AI Agents Build RAG Systems for Knowledge Base Chatbots
By
–
AI agents can build RAG systems, allowing you to chat easily with your knowledge bases.
— Abacus.AI (@abacusai) 26 juin 2024
This is a quick and easy way to apply LLMs in business settings pic.twitter.com/So1t8C4dQbAI agents can build RAG systems, allowing you to chat easily with your knowledge bases. This is a quick and easy way to apply LLMs in business settings
-
New Open LLM Leaderboard: Qwen 72B Dominates Chinese Models
By
–
Pumped to announce the brand new open LLM leaderboard. We burned 300 H100 to re-run new evaluations like MMLU-pro for all major open LLMs! Some learning:
– Qwen 72B is the king and Chinese open models are dominating overall
– Previous evaluations have become too easy for recent -
New Claude AI: Complete test and comparison with ChatGPT
By
–
The new Claude AI came out today and it's just INCREDIBLE! Claude 3.5 Sonnet, Artifacts, and GPTs version
@AnthropicAI
… Here's my complete test → https://youtu.be/RYSWmDqydi8 So, better than #ChatGPT?
