Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This is a GGUF conversion of Google's UMT5 xxl model, specifically the encoder part.
Model source
Source description
This is a GGUF conversion of Google's UMT5 xxl model, specifically the encoder part.
The weights can be used with ./llama-embedding or with the ComfyUI-GGUF custom node together with image/video generation models.
This is a quant as llama.cpp doesn't support imatrix creation for T5 models at the time of writing. It's therefore recommended to use for the best results, although smaller models may also still provide decent results in resource constrained scenarios.
Sources
1 sourceVerified Oct 2
Model artifacts
10 artifactsSource excerpts
2 excerpts--- base_model: google/umt5-xxl library_name: gguf license: apache-2.0 quantized_by: city96 language: en --- This is a GGUF conversion of [Google's UMT5 xxl model](https://huggingface.co/google/umt5-xxl), specifically the encoder part. The weights can be used with [`./llama-embedding`](https://github.com/ggerganov/llama.cpp/tree/master/examples/embedding) or with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node together with image/video generation models. This is a **non imatrix** quant as llama.cpp doesn't support imatrix creation for T5 models at the time of writing. It's therefore recommended to use **Q5_K_M or larger** for the best results, although smaller models may also still provide decent results in resource constrained scenarios.
umt5-xxl-encoder-Q3_K_M.gguf
gguf · 2.85 GB · SHA-256 b7e2ca4c493c…dba7 · Hugging Face
Source context: 222304 downloads · 190 likes · Library gguf · Repo city96/umt5-xxl-encoder-gguf
