Was just trying out the @huggingface R1 reproduction pipeline and saw they are recommending and using uv now too https://
github.com/huggingface/op
en-r1
…
OPEN SOURCE
-
Hugging Face R1 reproduction pipeline adopts uv tool
By
–
-
Sonar Deep Research now on Perplexity API
By
–
Sonar Deep Research is now available via Perplexity API with 60k tokens context length.
-
Dolphin LLM Series Accelerated by Cerebras for Open-Source AI
By
–
"Alignment should be a product feature, not a model constraint."
— Cerebras (@cerebras) 25 février 2025
That's the idea behind @cognitivecompai's leadership in open-source AI, with their Dolphin LLM series, now accelerated by Cerebras. ⚡
Cerebras helped them achieve:
– 5M+ training samples seamlessly processed
-… pic.twitter.com/vcJS5MFGCH"Alignment should be a product feature, not a model constraint." That's the idea behind @cognitivecompai
's leadership in open-source AI, with their Dolphin LLM series, now accelerated by Cerebras. Cerebras helped them achieve: – 5M+ training samples seamlessly processed
– -
FastRTC: Python Framework for Real-Time Voice AI Applications
By
–
AI models now handle voice/speech yet building w. them in Python is very frustrating Welcome FastRTC here to solve
– Automatic Voice Detection
– Handling WebRTC & the backend for real-time apps
– Calling Phones Blog https://
huggingface.co/blog/fastrtc
Github https://
github.com/freddyaboulton
/fastrtc
… -
LangGraph.js Supervisor: Multi-Agent Hierarchical Systems
By
–
LangGraph.js Supervisor A lightweight library for building hierarchical multi-agent systems with LangGraph – Create a supervisor agent to orchestrate multiple specialized agents – Tool-based handoffs for agent communication – Built with LangGraph.js: comes with
-
Grok-2 Open-Source Release Plans from Elon Musk
By
–
Indeed I was talking about *open-source* SOTA large models but Grok-2 will be soon open-source, right @elonmusk
-
DeepSeek MoE Architecture for Large Language Models
By
–
Let me add a bit context to the latest DeepSeek code release as I feel it was a bit bare bones. Mixture-of-Experts (MoE) is a simple extension of transformers which is rapidly establishing itself as be the go-to architecture for mid-to-large size LLM (20B-600B parameters). It
-
DeepSeek R1 Model Now Available on Hugging Face
By
–
🟩🟩
— SambaNova (@SambaNovaAI) 25 février 2025
🟩
🟩🟩🟩🟥 🟨
🐍 Sorry… just playing Snake thanks to our @deepseek_ai R1 model on @huggingface 🐍
What will you build on SambaNova Cloud? 👇Sorry… just playing Snake thanks to our @deepseek_ai R1 model on @huggingface What will you build on SambaNova Cloud?
-
Claude 3.7 Sonnet: Details and Announcements
By
–
Source
https://anthropic.com/news/claude-3-7-sonnet
… -
Claude Sonnet 3.7 excels in SWE benchmarks
By
–
Claude Sonnet 3.7 evals are here too A huge jump on the SWE bench