HN Explorer

michaelnny

↗ HN profile [ 82.3 ms ] full profile
Karma
23
Created
December 15, 2023 (2y ago)
Submissions
0
  1. Show HN: Fine-tune llama3 model to support function calling (github.com)

    Few weeks ago, we were tasked to make llama3 model to do function calling and build an API similar/compatible with OpenAI's python client. While we're still improving our dataset and FastAPI backend server (which can't…

    3 points 5
  2. Ask HN: The correct prompt/response format to fine-tune LLM for function call

    Hi, we’re working on deploying llama3 models on a private server for a corporate, however we found that llama3 does not support function calling. And now we try to fine-tune it on our own. After checking on the internet…

    1 points 1
  3. America Is Getting Ready for Space Warfare (wsj.com)
    3 points 1
  4. Ask HN: How do you handle routing/authorization for large-scale React project?

    Hi, I'm interested in how do professionals handle routing, authorization, and code/project management for enterprise-level React or Next.js application, here's a list to describe the situation: 1. The application are…

    1 points 2
  5. Microsoft Asks China-Based AI Staff to Consider Relocating to US (wsj.com)
    7 points 1
  6. Show HN: QLoRA-LLM – A custom implementation of QLoRA for fine-tuning a LLM (vectortheta.com)
    1 points 0