Running 869 869 FineWeb: decanting the web for the finest text data at scale 🍷 Generate high-quality web text data for LLM training
Molmo Collection Artifacts for open multimodal language models. • 5 items • Updated 24 minutes ago • 299
Qwen2 Collection Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Nov 28, 2024 • 359
DBRX Collection DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27, 2024 • 94