HN Explorer

rawsh

↗ HN profile [ 117 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels (nanduruganesh.github.io)
    1 points 5
  2. Zyphra ZAYA1-base: First large-scale model trained on AMD (zyphra.com)
    6 points 1
  3. Debugging divergence between engine and transformers logprobs for RL (gist.github.com)
    2 points 0
  4. Batched reward model inference and Best-of-N sampling (raw.sh)
    34 points 0
  5. Teaching LLMs to solve chess puzzles with DSPy and Finetuning (raw.sh)
    1 points 0
  6. Teaching chat models to solve chess puzzles (raw.sh)
    4 points 0
  7. Ask HN: Why aren't there Open source embedding models with context length > 512?
    3 points 2
  8. Show HN: DankGPT – Chat with Your Documents (dankgpt.com)

    Uses hybrid semantic search (combination of dense embeddings and sparse vectors) to retrieve high quality answers across your documents. Features - Significantly faster than competition (Process a 200 page PDF in <5s) -…

    17 points 9
  9. Show HN: Search PDFs in the browser using PDFgrep compiled to WebAssembly (pdfgrep.com)

    pdfgrep.org is a CLI tool I use a lot to reference documents from classes. I’ve been playing around with Emscripten and I wanted to make a UI version of the tool. All documents stay local so there is no upload time, and…

    4 points 1
  10. Show HN: Search PDFs using WASM in the browser (pdfgrep.com)

    pdfgrep.org is a CLI tool I use a lot to reference documents from classes. I’ve been playing around with Emscripten and I wanted to make a UI version of the tool. All documents stay local so there is no upload time, and…

    2 points 0