From 175d24931578ca87596cf2331911b39aa8b28aa7 Mon Sep 17 00:00:00 2001 From: mudler <2420543+mudler@users.noreply.github.com> Date: Mon, 29 Jun 2026 01:16:09 +0000 Subject: [PATCH] chore(model gallery): :robot: add new models via gallery agent Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- gallery/index.yaml | 69 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index ac825cdae028..3b2bffd9f01e 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,4 +1,73 @@ --- +- name: "unlimited-ocr" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/sahilchachra/Unlimited-OCR-GGUF + description: | + Unlimited OCR Works + + Welcome the Era of One-shot Long-horizon Parsing. + + ## Release + - [2026/06/28] 🤝 Thanks to the vLLM community and Tianyu Guo for their support, our model now supports vLLM inference. + - [2026/06/24] 🤝 Thanks to AK for creating a demo for us. It is now available at Hugging Face Spaces. + - [2026/06/23] 📄 Our paper is now available on arXiv. + - [2026/06/23] 🤝 Thanks to the ModelScope community for their support. Our model is now available at ModelScope. + - [2026/06/22] 🚀 We present Unlimited-OCR, aiming to push Deepseek-OCR one step further. + + ## Inference + + ### Transformers + Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.3 + CUDA12.9: + + ``` + torch==2.10.0 + torchvision==0.25.0 + transformers==4.57.1 + Pillow==12.1.1 + matplotlib==3.10.8 + einops==0.8.2 + addict==2.4.0 + easydict==1.13 + pymupdf==1.27.2.2 + psutil==7.2.2 + ``` + + ```python + import os + import torch + from transformers import AutoModel, AutoTokenizer + + model_name = 'baidu/Unlimited-OCR' + + ... + license: "mit" + tags: + - llm + - gguf + - multimodal + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + mmproj: llama-cpp/mmproj/Unlimited-OCR-GGUF/mmproj-Unlimited-OCR-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Unlimited-OCR-GGUF/Unlimited-OCR-Q4_K_M.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Unlimited-OCR-GGUF/Unlimited-OCR-Q4_K_M.gguf + sha256: c8461bded976eac709a33f6b26e1414efcd2124a203f2ee93ee984a4c9e9265b + uri: https://huggingface.co/sahilchachra/Unlimited-OCR-GGUF/resolve/main/Unlimited-OCR-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Unlimited-OCR-GGUF/mmproj-Unlimited-OCR-F16.gguf + sha256: 4f28c295e1fcf67a97488e356f2b4372da4702b77fdfad0fa138b5821325743c + uri: https://huggingface.co/sahilchachra/Unlimited-OCR-GGUF/resolve/main/mmproj-Unlimited-OCR-F16.gguf - name: "qwen-agentworld-35b-a3b" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: