Live data from Hacker News

Viewing profile — alanzhuly

alanzhuly

HN member
Joined
Mon, Feb 07, 2022, 6:14 PM UTC
HN karma
147
Public activity
39 items

About alanzhuly

Advancing on-device AI.

Personal website: https://www.alanzhuly.com/

Recent public activity

  1. story
  2. story
  3. story
  4. story
  5. story
  6. story
  7. comment
    Comment #42209288

    Hi! I am from Nexa AI. We just improved Omnivision-968M based on your feedback! Here is a preview in our Hugging Face Space: https://huggingface.co/spaces/NexaAIDev/omnivlm-dpo-dem…

  8. story
  9. story
  10. comment
    Comment #41966396

    If we can have this running locally on mobile phone that would be pretty cool. Imagine receiving a work document (for example, product requirement documents), and then this turning…

  11. comment
    Comment #41938206

    Hi Everyone! We built an open-sourced tool to benchmark GGUF models with a single line of code. GitHub Link: https://github.com/NexaAI/nexa-sdk/tree/main/nexa/eval Motivations: GGU…

  12. story
  13. story
  14. story
  15. comment
    Comment #41660639

    Thanks for reporting. We are investigating this issue. Could you help submit an issue to our GitHub and provide a screenshot of the terminal (with pip show nexaai)? This could help…

  16. comment
    Comment #41654614

    Llama3.2 3B feels a lot better than other models with same size (e.g. Gemma2, Phi3.5-mini models). For anyone looking for a simple way to test Llama3.2 3B locally with UI, Install …

  17. comment
    Comment #41612737

    For anyone looking for a simple alternative for running local models beyond just text, Nexa AI has built an SDK that supports text, audio (STT, TTS), image generation (e.g., Stable…

  18. comment
    Comment #41612678

    I like the latest qwen2.5 ( https://nexaai.com/Qwen/Qwen2.5-0.5B-Instruct/gguf-q4_0/read... ). It was just released last week. It is one of the best small langauge models right now…

  19. story
    Show HN: We built a knowledge hub for running LLMs on edge devices

    Hey HN! Alex and Zack from Nexa AI here. We are excited to share a project our team has been passionately working on recently, in collaboration with Jiajun from Meta, Qun from San …

  20. story
  21. comment
    Comment #40610694

    Our models work on both mobile apps and web apps. You can use our model's API, which is flexible and can be integrated with any code.

  22. comment
    Comment #40610508

    Currently, to modify the defined functions in the model, you can provide us with a description of your desired functions, and we can customize (fine-tune) a model for you. However,…

  23. comment
    Comment #40610230

    Our models can handle diverse user inputs well and have high accuracy in our benchmark results. Feel free to check it out here: https://huggingface.co/NexaAIDev/Octopus-v2/blob/mai…

  24. comment
    Comment #40610114

    Our models offer developers faster, cheaper alternative to GPT-4o for implementing function-calling AI agent workflows. Developers can use our model APIs and implement each model's…

  25. story
    Show HN: Use functional tokens for AI agents to simplify app workflows

    Hi HN! I want to share our latest project at NEXA AI. We developed AI agent foundation models designed to transform how developers create AI agent powered apps. One major challenge…