Instructions to use nomadoor/clef with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use nomadoor/clef with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
# No code snippets available yet for this library.
# To use this model, check the repository files and the library's documentation.
# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.jsClef (ComfyUI)
Cloudflare/clef-flash as a single file for ComfyUI. The weights are unchanged except for the format.
| File | Format |
|---|---|
clef_flash_bf16 |
bf16, as released |
clef_flash_int8_convrot |
int8 ConvRot |
Each file carries the joint schema head (clef_head.*, bf16) and joint_head_config.json (metadata clef_head_config), unchanged from the original repository. The backbone keys are the released ones, merged from the shards. In the int8 file, only the language-model linear layers are quantized, in ComfyUI's comfy_quant format (ConvRot group 256 with per-row scales). Embeddings, lm_head (the head reads its rows), norms and the vision encoder stay bf16.
Put one file in ComfyUI/models/text_encoders and use it with ComfyUI-TypedDecision: pick clef as the adapter and the file as the backbone.
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support