Back to directory

CSGHub

An open-source platform for managing large language models and their related assets, such as datasets, spaces and code, with upload, download, storage, verification and distribution through a web interface, git, a chatbot or an SDK.

CSGHub

CSGHub is an open-source platform for managing large language model assets. It handles the full lifecycle of LLMs and related assets such as datasets, spaces and code, letting users upload, download, store, verify and distribute assets like DeepSeek and Llama models through a web interface, the git command line, a natural-language chatbot, or the CSGHub SDK, which is compatible with the Hugging Face Python SDK.

It includes microservice submodules and standardized OpenAPIs for integration with existing systems, and can be deployed on-premises for offline operation, functioning as a private, self-hosted counterpart to Hugging Face. Features include model capability optimization, a space and asset management assistant, multi-source data synchronization, access control, and end-to-end data processing with annotation.

It offers both open-source and on-premises or SaaS deployment options.

More in Models

See all 405
  • mini-AGI

    github.com

    A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.

  • An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.

  • peekaboolean

    github.com

    A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.