{"id":16401886,"url":"https://github.com/notyusheng/multimodal-large-language-model","last_synced_at":"2025-04-21T11:33:11.220Z","repository":{"id":246463079,"uuid":"806457838","full_name":"NotYuSheng/Multimodal-Large-Language-Model","owner":"NotYuSheng","description":"Localized Multimodal Large Language Model (MLLM) integrated with Streamlit and Ollama for text and image processing tasks.","archived":false,"fork":false,"pushed_at":"2025-04-12T16:09:46.000Z","size":7730,"stargazers_count":4,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-12T17:23:37.506Z","etag":null,"topics":["docker","large-language-models","llava","llm","multimodal","multimodal-large-language-models","ollama","pretrained","python","sphinx-doc","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NotYuSheng.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":".github/SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-05-27T08:34:42.000Z","updated_at":"2025-04-12T16:09:24.000Z","dependencies_parsed_at":"2024-06-28T04:39:37.060Z","dependency_job_id":"7459eba1-c46c-4cf0-a8a1-22dbfce24357","html_url":"https://github.com/NotYuSheng/Multimodal-Large-Language-Model","commit_stats":null,"previous_names":["notyusheng/multimodal-large-language-model"],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NotYuSheng%2FMultimodal-Large-Language-Model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NotYuSheng%2FMultimodal-Large-Language-Model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NotYuSheng%2FMultimodal-Large-Language-Model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NotYuSheng%2FMultimodal-Large-Language-Model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NotYuSheng","download_url":"https://codeload.github.com/NotYuSheng/Multimodal-Large-Language-Model/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250048100,"owners_count":21366176,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["docker","large-language-models","llava","llm","multimodal","multimodal-large-language-models","ollama","pretrained","python","sphinx-doc","streamlit"],"created_at":"2024-10-11T05:44:27.517Z","updated_at":"2025-04-21T11:33:11.207Z","avatar_url":"https://github.com/NotYuSheng.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multimodal-Large-Language-Model (MLLM)\n\n\u003c!-- ![GitHub repo size](https://img.shields.io/github/repo-size/NotYuSheng/Multimodal-Large-Language-Model) --\u003e\n[![GitHub last commit](https://img.shields.io/github/last-commit/NotYuSheng/Multimodal-Large-Language-Model?color=red)](#)\n[![Sphinx](https://img.shields.io/badge/Sphinx-000?logo=sphinx\u0026logoColor=fff)](https://notyusheng.github.io/Multimodal-Large-Language-Model/index.html)\n\nThank you for checking out the Multimodal-Large-Language-Model project. Please note that this project was created for research purposes.\n\nFor a more robust and well-developed solution, you may consider using [open-webui/open-webui](https://github.com/open-webui/open-webui) with [ollama/ollama](https://github.com/ollama/ollama).\n\n\u003c!-- [[🤗Space DEMO](https://huggingface.co/spaces/NotYuSheng/MMLLM)] --\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"sample-img/LHC-DEMO.png\" alt=\"Demo image\" /\u003e\n\u003c/div\u003e\n\n## Documentation\nYou can access the project documentation at [[GitHub Pages](https://notyusheng.github.io/Multimodal-Large-Language-Model/)].\n\n## Host requirements\n- **Docker**: [[Installation Guide](https://docs.docker.com/engine/install/)]\n- **Docker Compose**: [[Installation Guide](https://docs.docker.com/compose/install/)]\n- Compatibile with Linux and Windows Host\n- Ensure port 8501 and 11434 are not already in use\n- You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models. [[Source](https://github.com/ollama/ollama)]\n- Project can be ran on either CPU or GPU\n\n### Running on GPU\n- **NVIDIA Container Toolkit** (Linux) [[Installation Guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)]\n- **NVIDIA CUDA Toolkit** (Windows) [[Installation](https://developer.nvidia.com/cuda-downloads)]\n- **WSL** (Windows) [[Installation](https://docs.docker.com/desktop/gpu/)]\n\n## Tested Model(s)\n| Model Name | Size | Link |\n| --- | --- | --- |\n| llava:7b | 4.7GB | [Link](https://www.ollama.com/library/llava:7b) |\n| llava:34b | 20GB | [Link](https://www.ollama.com/library/llava:34b) |\n\nLlava is pulled and loaded by default, other models from [Ollama](https://www.ollama.com/library) can be added into [ollama/ollama-build.sh](ollama/ollama-build.sh)\n\n## Usage\n\u003e [!NOTE] \nProject will run on GPU by default. To run on CPU, use the `docker-compose.cpu.yml` instead\n\n1.  Clone this repository and navigate to project folder\n```\ngit clone https://github.com/NotYuSheng/Multimodal-Large-Language-Model.git\ncd Multimodal-Large-Language-Model\n```\n\n2.  Build the Docker images:\n```\ndocker compose build\n```\n\n3.  Run images\n```\ndocker compose up -d\n```\n\n4.  Access Streamlit webpage from host\n```\n\u003chost-ip\u003e:8501\n```\n\nAPI calls to Ollama server can be made to\n```\n\u003chost-ip\u003e:11434\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnotyusheng%2Fmultimodal-large-language-model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnotyusheng%2Fmultimodal-large-language-model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnotyusheng%2Fmultimodal-large-language-model/lists"}