Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
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.
116
ConvFill: Inference-Time Knowledge Transfer
Model weights, dataset, and paper for https://arxiv.org/abs/2511.07397.
5
DoctoBERT-fr
French medical encoders pretrained from scratch on curated and LLM-rephrased medical web data.
8
APEX Quants (GGUF)
MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant )
121
💻 Qwopus-Coder
Reasoning-distilled coding models optimized for specialized domains like agentic workflows.
30
Qwen3
Collection by
Dec 31, 2025
1820
Apertus Mini
Distillations and Quantizations of our models into more compact formats (<8B parameters)
8
Nemotron-Post-Training-v3
Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3.
168
💻 Qwopus-Coder
Reasoning-distilled coding models optimized for specialized domains like agentic workflows.
30
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.
116
Qwen3
Collection by
Dec 31, 2025
1820
ConvFill: Inference-Time Knowledge Transfer
Model weights, dataset, and paper for https://arxiv.org/abs/2511.07397.
5
DoctoBERT-fr
French medical encoders pretrained from scratch on curated and LLM-rephrased medical web data.
8
Apertus Mini
Distillations and Quantizations of our models into more compact formats (<8B parameters)
8
APEX Quants (GGUF)
MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant )
121
Nemotron-Post-Training-v3
Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3.
168