Hugging Face Hub
Named by 13 kept items in this workspace.
The items that name it 13
Open infrastructure for hosting and sharing scientific datasets, models and code in AI-ready formats; Hugging Face is the infrastructure partner for Project ProtoStar and is among the ten generalist repositories listed by NIH for sharing research data
Hosts the open-weight LFM3 collection and model cards.
Hosts the Kumo Relational weights at nvidia/Kumo-Relational.
Platform for sharing exported policies, ideally with a short model card and training configuration.
Hosts Neuron kernels and trained checkpoints.
Hosts model weights such as Fish Audio Drama-3.
Hosts checkpoints, datasets and trained adapters (diffusers-modular/flux3-tarot-lora)
Platform where the resulting models and datasets are published publicly, each with an evaluation in its model card.
Hosts and versions RL environments like datasets.
Stores dataset repos, versions them, gates them, previews them, and serves them; now shows an RL Environments filter for datasets tagged rl-environment.
Hosts every published artifact (datasets, models, rollouts) gathered in one collection
hosts shared funes memories as private-by-default datasets, supplying ownership, access control, versioning, distribution, caching, and content-dedup
Source of any text-generation model Soup can fine-tune, provided it loads with AutoModelForCausalLM
In every workspace you can read 14
AI
All technologies in this workspace.