Collections

Foundation models for human tasks. Code: https://github.com/facebookresearch/sapiens

Multilingual multi-task general text embedding model

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B.

Spaces and utilities for creating datasets and getting them on the Hub