Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
These are quantizations of the model PaddleOCR-VL-1.5
Model source
Source description
These are quantizations of the model PaddleOCR-VL-1.5
Download the latest llama.cpp to use them.
Try to use the best quality you can run.
For the mmproj, try to use the F32 version as it will produce the best results.
F32 > BF16 > F16
Includes chat template fix from https://github.com/ggml-org/llama.cpp/pull/18825
Sources
1 sourceVerified Sep 10
Model artifacts
6 artifactsSource excerpts
2 excerpts--- pipeline_tag: image-to-text base_model: - PaddlePaddle/PaddleOCR-VL-1.5 --- These are quantizations of the model [PaddleOCR-VL-1.5](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5) Download the latest llama.cpp to use them. Try to use the best quality you can run. For the mmproj, try to use the F32 version as it will produce the best results. F32 > BF16 > F16 Includes chat template fix from https://github.com/ggml-org/llama.cpp/pull/18825
mmproj-F32.gguf
gguf · 1.64 GB · SHA-256 b7c400854a08…bec9 · Hugging Face
Source context: 308 downloads · 11 likes · Pipeline image-to-text · Repo noctrex/PaddleOCR-VL-1.5-GGUF
