HN Explorer

joennlae

↗ HN profile [ 390 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Different Sampling Strategies for LLMs (huggingface.co)
    1 points 0
  2. Show HN: Stella Nera – Maddness Hardware Accelerator (github.com)
    154 points 27
  3. Show HN: Maddness – Energy-efficient DNNs without multiplying (arxiv.org)
    2 points 0
  4. Show HN: less than 650 LOC trainable GPT only using NumPy (github.com)
    90 points 18
  5. Show HN: Tensorli – NumPy Only Transformer Training (<650 lines) (github.com)
    2 points 0
  6. GithubNext: AI-Powered Auto-Fix Pull Requests for Issues (githubnext.com)
    3 points 0
  7. Show HN: Tensorli - GPT-Like Transformers in Pure NumPy (github.com)
    3 points 0
  8. Nvidia uses internal LLM to support chip design efforts (blogs.nvidia.com)
    2 points 0
  9. “THIS-IS-NOT-A-BACKUP” forking popular FOSS repos with a cron job (github.com)
    1 points 0