omneity
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Tokenization Is Killing Our Multilingual LLM Dream (huggingface.co)
- A Wordle for the Worldle (omarkamali.com)
- Show HN: Wikilangs Games – Wordle-like for 300 Languages (games.wikilangs.org)
- Show HN: Picomon, a minimal TUI monitor for AMD GPUs (github.com)
- Meta Synthetic Data Kit (github.com)
- Getting Perfectly Structured Data from LLMs (omarkama.li)
- Finding Moroccan Arabic (Darija) in the Fineweb 2 Dataset (huggingface.co)
- Copied Act would make removing AI digital watermarks illegal (theverge.com)
- An African Superstate: The East African Federation (2022) (karlsnotes.com)
- Mixtral 8x7B on 24GB VRAM (2-bit quantized) (twitter.com)
- OpenAI RAG: A Step Forward or a Step Too Far? (omarkama.li)
- OpenAI's RAG: A Step Forward or A Step Too Far? (omarkama.li)
- Web Scraping: Data for Everyone (omarkama.li)
- What Is Data: A Brief Guide (omarkama.li)