Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
LTX-2.3 Creative Lab
LoRAs and IC-LoRAs, trained on the LTX-2.3 model
Heretic - Abliterated, Uncensored, Unrestricted POWER.
Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model.
MedGemma Release
Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications.
Agents-A1
Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.
Nemotron-Post-Training-v3
Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3.
Agents-A1
Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.
LTX-2.3 Creative Lab
LoRAs and IC-LoRAs, trained on the LTX-2.3 model
Nemotron-Post-Training-v3
Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3.
Heretic - Abliterated, Uncensored, Unrestricted POWER.
Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model.
MedGemma Release
Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications.