Notes
- These models are too damn big!
- Enjoying El Sonido from KEXP
- New podcast (Better Offline) added to blogroll
- Week of April 07, 2024 - Post Summary
Responses
- LLM training in simple, raw C/CUDA
- RecurrentGemma - Open weights language model from Google DeepMind, based on Griffin.
- Beeper was just acquired by Automattic
- Hello OLMo: A truly open LLM
- Molly White's Blogroll
- ARAGOG: Advanced RAG Output Grading
- Rock AlterLatino from Radio Bilingue
- Far Out Guides
- Proton and Standard Notes are joining forces
- DE-COP: Detecting Copyrighted Content in Language Models Training Data
- Using LLM to select the right SQL Query from candidates
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models