{"id":18573924,"url":"https://github.com/odynvolk/jensen","last_synced_at":"2025-04-10T07:32:41.017Z","repository":{"id":187541126,"uuid":"677104080","full_name":"odynvolk/jensen","owner":"odynvolk","description":"A LLaMA 2 powered Telegram chatbot.","archived":false,"fork":false,"pushed_at":"2024-02-11T13:07:49.000Z","size":19,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-18T22:08:35.882Z","etag":null,"topics":["chatbot","llama2","llamacpp","llm","telegram"],"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/odynvolk.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}},"created_at":"2023-08-10T18:42:45.000Z","updated_at":"2024-06-13T02:18:11.000Z","dependencies_parsed_at":"2023-08-11T01:30:42.837Z","dependency_job_id":"a26f99d4-eebe-4581-b791-2470a2f393d6","html_url":"https://github.com/odynvolk/jensen","commit_stats":null,"previous_names":["odynvolk/jensen"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/odynvolk%2Fjensen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/odynvolk%2Fjensen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/odynvolk%2Fjensen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/odynvolk%2Fjensen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/odynvolk","download_url":"https://codeload.github.com/odynvolk/jensen/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223430221,"owners_count":17143625,"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":["chatbot","llama2","llamacpp","llm","telegram"],"created_at":"2024-11-06T23:13:24.468Z","updated_at":"2025-04-10T07:32:41.009Z","avatar_url":"https://github.com/odynvolk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# jensen\n\nA LLM powered Telegram bot.\n\n## Prerequisites:\n\n### Telegram bot\n\nFirst you need to create a Telegram bot to interact with. See instructions [here](https://core.telegram.org/bots).\n\n### LLM model\n\nYou need a LLM in GGUF format. You can find quite a few through [TheBloke on HuggingFace](https://huggingface.co/TheBloke)\nwho has done an enormous service to the community by converting different models to GGUF and quantized them. Pick one that suits your\nneeds and hardware requirements.\n\n### Python\n\nYou need Python 3 on your machine.\n\n- Micromamba (optional)\n\nFor handling the packages needed for different enivronments. Easy to install with asdf.\n\n```bash\n$ asdf install\n$ micromamba create -n jensen python=3.13\n$ micromamba activate jensen\n```\n\n- LLMs, Telegram etc\n\nFor using LLM models, Telegram API etc\n\n```bash\n$ pip install -r requirements.txt\n```\n\n## Configuration\n\nCreate a `.env` file with the following properties.\n\n```\n# LLM\nMODEL_PATH=\u003cpath to model file, string\u003e (mandatory)\nMAX_TOKENS=\u003cmax tokens, int\u003e\nN_CTX=\u003cnumber of context, int\u003e\nN_GPU_LAYERS\u003chow many layers to offload to the GPU, int\u003e\nN_THREADS=\u003cnumber of threads to use for Llama usage, int\u003e\nUSE_MLOCK=\u003cforce the system to keep the model in RAM., bool\u003e\n\n# Telegram\nAPI_KEY=\u003capi key, string\u003e (mandatory)\nPOLL_INTERVAL=\u003cinterval to use when polling Telegram as seconds, float\u003e\n```\n\n## Usage\n\nStart the application:\n\n```bash\npython ./jensen/app.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fodynvolk%2Fjensen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fodynvolk%2Fjensen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fodynvolk%2Fjensen/lists"}