Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
Bielik-7B-v0.1
A collection of models based on Bielik-7B-v0.1 - base model, instructional and quantized versions, and MLX (Apple).
LayerSkip
Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710
Spaces for Text-to-images (SDXL, Pony, SD1.5, Flux,...)
Collection by
4 days ago
Qwen2
Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B.
Russian Models
A small collection of models who can communicate well in Russian. Almost all of them also available in gguf. Saiga, Vikhr, rugpt are excluded.
Blackhole
A black hole with lots of high-quality dialogue datasets in many fields, and multilingual helps to train LLMs with SFT and DPO methods easier.
Bielik-7B-v0.1
A collection of models based on Bielik-7B-v0.1 - base model, instructional and quantized versions, and MLX (Apple).
LayerSkip
Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710
Spaces for Text-to-images (SDXL, Pony, SD1.5, Flux,...)
Collection by
4 days ago
Qwen2
Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B.
Russian Models
A small collection of models who can communicate well in Russian. Almost all of them also available in gguf. Saiga, Vikhr, rugpt are excluded.
Blackhole
A black hole with lots of high-quality dialogue datasets in many fields, and multilingual helps to train LLMs with SFT and DPO methods easier.