Open Source PM at Nexa AI, advancing on-device AI.
- How to unify Gemma and Whisper to build a super fast local voice LLM
by alanzhuly on 12/17/24, 8:53 PM, with comments
- What you can do with tiny (1B/3B) LLMs in a local RAG system?
by alanzhuly on 11/5/24, 8:31 PM, with comments
- Benchmark GGUF model with ONE line of code
by alanzhuly on 10/24/24, 6:29 PM, with comments
- Llama.cpp Now Part of the Nvidia RTX AI Toolkit
by alanzhuly on 10/3/24, 6:31 PM, with comments
- Small Language Models: Survey, Measurements, and Insights
by alanzhuly on 9/26/24, 8:50 PM, with comments
- Show HN: We built a knowledge hub for running LLMs on edge devices
by alanzhuly on 9/5/24, 12:37 PM, with comments
- Join Super AI Agent Hackathon at Stanford, Hosted by HuggingFace and Nexa AI
by alanzhuly on 6/26/24, 5:54 PM, with comments
- Show HN: Use functional tokens for AI agents to simplify app workflows
by alanzhuly on 6/7/24, 4:01 PM, with comments
- Google confirms the leaked Search documents are real
by alanzhuly on 5/29/24, 10:50 PM, with comments
- Recovering 4D World from Monocular Video
by alanzhuly on 5/29/24, 4:59 PM, with comments
- Privacy-Aware Visual Language Models
by alanzhuly on 5/28/24, 10:45 PM, with comments
- Transformers Can Do Arithmetic with the Right Embeddings
by alanzhuly on 5/28/24, 5:03 PM, with comments
- Aya 23: Open Weight Releases to Further Multilingual Progress
by alanzhuly on 5/28/24, 1:12 AM, with comments
- Feds add nine more incidents to Waymo robotaxi investigation
by alanzhuly on 5/24/24, 10:28 PM, with comments
- Elon Musk's XAI Secures New Backing from Andreessen Horowitz, Sequoia and Tribe
by alanzhuly on 5/23/24, 6:54 PM, with comments
- Neuralink's First User Is 'Constantly Multitasking' with His Brain Implant
by alanzhuly on 5/23/24, 6:59 AM, with comments
- Octopus V4: a graph of language models
by alanzhuly on 5/2/24, 11:06 PM, with comments