{"id":15164689,"url":"https://github.com/lmlk-seal/llmodel","last_synced_at":"2026-01-26T01:32:08.158Z","repository":{"id":252460864,"uuid":"840512294","full_name":"LMLK-seal/LLModel","owner":"LMLK-seal","description":"Private LLModel GUI Chat allows users to interact with a local large language model (LLM) using the Llama library and GGUF models.","archived":false,"fork":false,"pushed_at":"2024-09-04T08:40:29.000Z","size":3478,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-20T16:04:31.275Z","etag":null,"topics":["ai","assistant","chatbot","code","cpu","gguf","gpu-computing","gui","llama","llamacpp","llm","model","models","offline","privacy","private","prompt","python","simple","virtual-assistant-ai"],"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/LMLK-seal.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2024-08-09T22:09:32.000Z","updated_at":"2025-01-13T07:07:14.000Z","dependencies_parsed_at":"2024-09-13T22:40:49.090Z","dependency_job_id":"3f91a064-3b09-480d-b060-1a02bdcf2318","html_url":"https://github.com/LMLK-seal/LLModel","commit_stats":{"total_commits":35,"total_committers":1,"mean_commits":35.0,"dds":0.0,"last_synced_commit":"86d366f1d72fb66ed703cdc9e60929ffd60df18e"},"previous_names":["lmlk-seal/llmodel"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LMLK-seal%2FLLModel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LMLK-seal%2FLLModel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LMLK-seal%2FLLModel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LMLK-seal%2FLLModel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LMLK-seal","download_url":"https://codeload.github.com/LMLK-seal/LLModel/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235383702,"owners_count":18981198,"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":["ai","assistant","chatbot","code","cpu","gguf","gpu-computing","gui","llama","llamacpp","llm","model","models","offline","privacy","private","prompt","python","simple","virtual-assistant-ai"],"created_at":"2024-09-27T03:43:21.843Z","updated_at":"2025-10-29T13:31:11.707Z","avatar_url":"https://github.com/LMLK-seal.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLModel: 100% Private-Offline chat!\n\n![LLModel Chat Demo](https://raw.githubusercontent.com/LMLK-seal/LLModel/main/LLModel1.gif)\n\nLLModel Chat is a CPU only PyQt5-based graphical user interface (GUI) application that allows users to interact with a local large language model (LLM) using the Llama library. This application provides a user-friendly interface for loading and using LLM models, engaging in conversations, and even processing uploaded text or PDF files as context for the AI responses.\n\n## Concept and Features\n\nThe main concept behind LLModel Chat is to provide an easy-to-use interface for interacting with local LLM models. It combines the power of LLMs with a clean, intuitive GUI, making it accessible for users who may not be comfortable with command-line interfaces.\n\nKey features include:\n\n1. **Model Loading**: Users can load a local GGUF (GPT-Generated Unified Format) model file.\n2. **File Upload**: Ability to upload and process text or PDF files as additional context for the AI.\n3. **Conversation Interface**: A chat-like interface for interacting with the AI model.\n4. **Adjustable Parameters**: Users can modify max tokens and temperature settings.\n5. **Code Extraction**: Automatically detects Python code in AI responses and allows downloading.\n6. **Progress Indication**: Shows the progress of AI response generation.\n7. **Conversation Management**: Option to clear the conversation history.\n8. **Text2Speech**: Option to play the AI response.\n9. **Copy text**: Option to copy the text of the AI response.\n10. **Save/load conversation**: Option to save and load previous conversations. \n\n## Libraries and Dependencies\n\nTo run this application, you'll need to install the following libraries:\n\n1. PyQt5: For the graphical user interface\n2. llama-cpp-python: For interfacing with the Llama models\n3. PyMuPDF (fitz): For handling PDF files.\n4. pyttsx3: Text to speech.\n\nYou can install these libraries using pip: \n```\n   pip install PyQt5 llama-cpp-python PyMuPDF pyttsx3\n   ```\n\n## How to Run the Code\n\n1. Ensure you have Python 3.6+ installed on your system.\n2. Install the required libraries as mentioned above.\n3. Download the `LLModel.py` file to your local machine.\n4. Open a terminal or command prompt and navigate to the directory containing `LLModel.py`.\n5. Run the script using Python:\n\n6. The LLModel Chat window should appear.\n\n## Using the Application\n\n1. **Load Model**: Click the \"Load Model\" button and select your GGUF model file.\n2. **Upload Context File** (Optional): You can upload a text or PDF file to provide additional context for the AI responses.\n3. **Start Chatting**: Type your message in the input field and click \"Send\" or press Enter.\n4. **Adjust Settings**: You can modify the max tokens and temperature using the controls at the bottom of the window.\n5. **Download Code**: If the AI generates Python code, you can download it using the \"Download Code\" button.\n6. **Clear Conversation**: Use the \"Clear Conversation\" button to start a new chat session.\n7. **Auto/Menual mode**: Use auto or menual mode for tokens count.\n\n## Note\n\nThis application requires a compatible GGUF model file to function. Make sure you have a suitable model before running the application. The model should be compatible with the llama-cpp-python library.\n\nGGUF libraries: \nhttps://huggingface.co/models?library=gguf\n\nRecommended GGUF models:\n1. Phi-3-mini-4k-instruct-gguf (Q5_K_M)\nhttps://huggingface.co/bartowski/Phi-3.1-mini-4k-instruct-GGUF\n\n2. Meta-Llama-3.1-8B-Instruct-GGUF (Q5_K_M)\nhttps://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF\n\n## Contribution\n\nContributions to improve the application are welcome. Please feel free to submit issues or pull requests to enhance functionality, fix bugs, or improve the user interface.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flmlk-seal%2Fllmodel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flmlk-seal%2Fllmodel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flmlk-seal%2Fllmodel/lists"}