rawsh
- Karma
- 30
- Created
- 5 years ago
Recent Submissions
- 1. ▲ Zyphra ZAYA1-base: First large-scale model trained on AMD (zyphra.com)
- 2. ▲ Debugging divergence between engine and transformers logprobs for RL (gist.github.com)
- 3. ▲ Batched reward model inference and Best-of-N sampling (raw.sh)
- 4. ▲ Teaching LLMs to solve chess puzzles with DSPy and Finetuning (raw.sh)
- 5. ▲ Teaching chat models to solve chess puzzles (raw.sh)
- 6. ▲ Ask HN: Why aren't there Open source embedding models with context length > 512?
- 7. ▲ Show HN: DankGPT – Chat with Your Documents (dankgpt.com)
- 8. ▲ Show HN: Search PDFs in the browser using PDFgrep compiled to WebAssembly (pdfgrep.com)
- 9. ▲ Show HN: Search PDFs using WASM in the browser (pdfgrep.com)