Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
These are quantizations of the model PaddleOCR-VL-1.5
Source du modèle
Description de la source
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 sourceVérifié 10 sept.
Artefacts du modèle
6 artefactsExtraits de sources
2 extraits--- 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
