did you finally cave to the PLZ FOR THE LOVE OF GOD TRY GEMINI, I BEG YOU call out?
LLMS
-
Ultravox 0.4.1: Open-Source Audio LM Approaching GPT-4o Level
By
–
Audio LMs scene is heating up! 🔥 @FixieAI Ultravox 0.4.1 – 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder, profit 💥
— Vaibhav (VB) Srivastav (@reach_vb) 16 novembre 2024
Bonus: MIT licensed checkpoints
> Pre-trained on Llama3.1-8b/ 70b backbone as well as the encoder part of… pic.twitter.com/uB6FNJZvRbAudio LMs scene is heating up! @FixieAI Ultravox 0.4.1 – 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder, profit Bonus: MIT licensed checkpoints > Pre-trained on Llama3.1-8b/ 70b backbone as well as the encoder part of
-
New LLM battles this weekend
By
–
Looks like there’s a new round of LLM battles on @lmarena_ai this weekend. – anonymous-chatbot – some reports suggest it’s an improved 4o with better formatting and instruction handling.
– secret-chatbot – potentially a larger Gemini-Exp model mentioned last week. -
Mistral to unveil three new models next week
By
–
According to the 'Limits' page on Le Platforme, Mistral AI is set to release three new models (reportedly as early as next week). – mistral-large-2411 – Potentially a multimodal Large 2.1
– pixtral-large-2411
– mistral-moderation-2411 – A compact model for moderation -
Groq 5th Developer Meetup: AMA and Product Demos
By
–
Thanks to all who attended our 5th Groq Developer Meetup. We had ,, an AMA with John Barrus, Head of Product, and 3 great demos from @GiampieroR73470 / https://
hubs.la/Q02YntXK0, Joe Hewett / https://
hubs.la/Q02YnwcY0 and @mceoin / https://
hubs.la/Q02YnkQW0. See you again in 2025! -
Groq Sponsors Meta’s Llama Impact Hackathon in London
By
–
@AIatMeta
's Llama Impact hackathon in London is going full swing! Stop by our table with any questions you have and grab swag. As always, we're offering increased rate limits, and can't wait to see what you build on Groq! Good luck to all of the hackers. cc @cerebral_valley -
LLM App Architecture: Single Call vs Complex Agent Patterns
By
–
Thinking of hot-take blogs to write next – which seem most interesting: – Why LLM apps should be either a single LLM call or complex agent
– Multi agent patterns
– Single agent → multi agent → LangGraph
– Updated agent UX takes other? (prev blogs: https://
blog.langchain.dev/tag/in-the-loo
p/
…) -
Nvidia LLaMA-Mesh: 3D Mesh Generation with Llama 3.1
By
–
Nvidia presents LLaMA-Mesh: Generating 3D Mesh with Llama 3.1 8B. Promises weights drop soon. pic.twitter.com/Aj6ZPSdbbH
— Chubby♨️ (@kimmonismus) 16 novembre 2024Nvidia presents LLaMA-Mesh: Generating 3D Mesh with Llama 3.1 8B. Promises weights drop soon.
