{"id":21403962,"url":"https://github.com/techn0man1ac/simplegpt","last_synced_at":"2026-05-07T12:31:09.575Z","repository":{"id":263469268,"uuid":"890509138","full_name":"techn0man1ac/SimpleGPT","owner":"techn0man1ac","description":"A simple implementation of a GPT-like model using TensorFlow and Keras. It uses a Transformer architecture with multi-head attention to generate responses from input questions.","archived":false,"fork":false,"pushed_at":"2024-11-24T20:31:37.000Z","size":176,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-23T03:29:49.584Z","etag":null,"topics":["dataset","keras","neural-network","tensorflow","trainn"],"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/techn0man1ac.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":"2024-11-18T17:33:11.000Z","updated_at":"2024-11-24T20:31:40.000Z","dependencies_parsed_at":"2024-11-26T07:00:48.354Z","dependency_job_id":null,"html_url":"https://github.com/techn0man1ac/SimpleGPT","commit_stats":null,"previous_names":["techn0man1ac/simplegpt"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/techn0man1ac%2FSimpleGPT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/techn0man1ac%2FSimpleGPT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/techn0man1ac%2FSimpleGPT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/techn0man1ac%2FSimpleGPT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/techn0man1ac","download_url":"https://codeload.github.com/techn0man1ac/SimpleGPT/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243901198,"owners_count":20366251,"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":["dataset","keras","neural-network","tensorflow","trainn"],"created_at":"2024-11-22T16:11:17.635Z","updated_at":"2026-05-07T12:31:09.515Z","avatar_url":"https://github.com/techn0man1ac.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Simple GPT Model\n\n![Chat with model](https://raw.githubusercontent.com/techn0man1ac/SimpleGPT/refs/heads/main/img/Screenshot.png)\n\nA simple implementation of a GPT-like model using TensorFlow and Keras. It uses a Transformer architecture with multi-head attention to generate responses from input questions.\n\n## Features\n\n- Transformer-based architecture with multi-head attention\n- Positional encoding added to input embeddings\n- Customizable hyperparameters (e.g., embedding size, number of layers)\n- Tokenizer-based input processing\n- Option to train from scratch or load a pre-trained model\n- Interactive question-answer generation\n\n## Requirements\n\nInstall dependencies:\n\n```bash\npip install tensorflow keras numpy\n```\n\n# Dataset\n\nThe model uses a custom dataset (simpleGPTDict) with question-answer pairs. Each pair is tokenized with \u003cstart\u003e and \u003cend\u003e tokens.\n\n# Model Overview\n\nInput: Tokenized question sequences\nArchitecture: Embedding → Positional Encoding → Transformer Encoder → Output Layer\nTraining: Uses SparseCategoricalCrossentropy loss and Adam optimizer\n\n# Running the Model\n\n## Train Model\n\nTo train the model, run:\n\n```bash\npython SimpleGPT.py\n```\n\nSelect option `1` to train from scratch. The trained model will be saved as `simple_gpt_model.keras`.\n\n## Load Pre-trained Model\n\nTo load an existing model, select option `0` when prompted.\n\n# Usage\n\nInteract with the model to generate responses:\n\n```bash\nQuestion: What is your name?\nResponse: i am eliks \n```\n\n# License\n\nThis project is licensed under the MIT License - see the [LICENSE](https://github.com/techn0man1ac/SimpleGPT/blob/main/LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftechn0man1ac%2Fsimplegpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftechn0man1ac%2Fsimplegpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftechn0man1ac%2Fsimplegpt/lists"}