SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper β’ 2502.02737 β’ Published 24 days ago β’ 195
Running 278 278 Kokoro Text-to-Speech (WebGPU) π£ High-quality speech synthesis powered by Kokoro TTS
Running on CPU Upgrade 4.92k 4.92k MTEB Leaderboard π₯ Select benchmarks and languages for text embeddings evaluation