{"id":22631675,"url":"https://github.com/ansonhex/llama3-nas","last_synced_at":"2025-04-11T20:04:23.407Z","repository":{"id":236413650,"uuid":"792557731","full_name":"ansonhex/Llama3-NAS","owner":"ansonhex","description":"This is a script to locally build Llama3 on NAS","archived":false,"fork":false,"pushed_at":"2024-04-27T00:09:19.000Z","size":1,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-11T20:04:14.756Z","etag":null,"topics":["llama3","nas"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ansonhex.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-26T23:32:51.000Z","updated_at":"2025-02-11T10:27:09.000Z","dependencies_parsed_at":"2024-04-27T01:25:59.296Z","dependency_job_id":"eef9e2f4-5d2f-4cd2-b208-0d0b3bf15552","html_url":"https://github.com/ansonhex/Llama3-NAS","commit_stats":null,"previous_names":["ansonhe97/llama3-nas","ansonhex/llama3-nas"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ansonhex%2FLlama3-NAS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ansonhex%2FLlama3-NAS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ansonhex%2FLlama3-NAS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ansonhex%2FLlama3-NAS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ansonhex","download_url":"https://codeload.github.com/ansonhex/Llama3-NAS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248473129,"owners_count":21109628,"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":["llama3","nas"],"created_at":"2024-12-09T02:10:42.786Z","updated_at":"2025-04-11T20:04:23.382Z","avatar_url":"https://github.com/ansonhex.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Running Llama3 on NAS\n\nThis is a simple instruction on how to locally run Llama3 on your NAS using [Open WebUI](https://github.com/open-webui/open-webui) and [Ollama](https://github.com/ollama/ollama). \n\n## Hardware\n\n- **[UGREEN NASync DXP480T Plus](https://www.kickstarter.com/projects/urgreen/ugreen-nasync-next-level-storage-limitless-possibilities?ref=9q75gj)**\n  - CPU: Intel® Core™ i5-1235U Processor (12M Cache, up to 4.40 GHz, 10 Cores 12 Threads)\n  - RAM: 8G\n\n## Setup Instructions\n\n### 1. Create Necessary Directories\n\nOpen a terminal and run the following commands to create directories for your AI models and the web interface:\n\n```sh\n$ mkdir -p /home/ansonhe/AI/ollama\n$ mkdir -p /home/ansonhe/AI/Llama3/open-webui\n```\n\n### 2. Deploy Using Docker\n\nCopy the provided `docker-compose.yml` file to your directory, then start the services using Docker:\n\n```sh\n$ sudo docker-compose up -d\n```\n\n### 3. Access the Web Interface\n\nOpen web browser and enter `YOUR_NAS_IP:8080`\n\n### 4. Configure Ollama Models\n\nIn the web interface, change the Ollama Models address to `0.0.0.0:11434`.\n\n![config](https://raw.githubusercontent.com/ansonhe97/rawimages/master/img/config.png)\n\n### 5. Download the Llama3 Model\n\nDownload the Llama3 Model **`ollama run llama3:8b`**, (Only using 8b versions here since performance limitations on NAS)\n\n![download](https://raw.githubusercontent.com/ansonhe97/rawimages/master/img/llama3-download.png)\n\n### 6. Set Llama3 as the Default Model\n\nAfter the model has been downloaded, you can select Llama3 as your default model and host it locally.\n\n![llama3](https://raw.githubusercontent.com/ansonhe97/rawimages/master/img/llama3-hello.png)\n\n## Performance Considerations\n\nPlease note that the CPU of the NAS may still face limitations when running large language models (LLMs) due to its processing capabilities.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fansonhex%2Fllama3-nas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fansonhex%2Fllama3-nas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fansonhex%2Fllama3-nas/lists"}