Top New Best Ask Show Jobs

rawsh

51 karma · joined May 5, 2020

submissions comments

Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels

nanduruganesh.github.io·41 pts·rawsh·

Zyphra ZAYA1-base: First large-scale model trained on AMD

zyphra.com·6 pts·rawsh·

Debugging divergence between engine and transformers logprobs for RL

gist.github.com·2 pts·rawsh·

Batched reward model inference and Best-of-N sampling

raw.sh·34 pts·rawsh·

Teaching LLMs to solve chess puzzles with DSPy and Finetuning

raw.sh·1 pts·rawsh·

Teaching chat models to solve chess puzzles

raw.sh·4 pts·rawsh·

Ask HN: Why aren't there Open source embedding models with context length > 512?

3 pts·rawsh·

Show HN: DankGPT – Chat with Your Documents

dankgpt.com·17 pts·rawsh·

Show HN: Search PDFs in the browser using PDFgrep compiled to WebAssembly

pdfgrep.com·4 pts·rawsh·

Show HN: Search PDFs using WASM in the browser

pdfgrep.com·2 pts·rawsh·