{"id":20226806,"url":"https://github.com/aastroza/modal-outlines-examples","last_synced_at":"2026-06-08T16:03:29.738Z","repository":{"id":234288157,"uuid":"788589967","full_name":"aastroza/modal-outlines-examples","owner":"aastroza","description":"Examples of code that use Outlines to enable structured text generation for LLMs running on Modal","archived":false,"fork":false,"pushed_at":"2024-04-25T20:12:53.000Z","size":38,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-13T23:35:16.339Z","etag":null,"topics":["cloud","generative-ai","gpu","json","llms","modal","outlines","serverless","structured-generation"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aastroza.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":"2024-04-18T17:57:28.000Z","updated_at":"2024-04-25T20:12:57.000Z","dependencies_parsed_at":"2024-04-25T21:27:47.841Z","dependency_job_id":"a6cb7637-2596-4f66-bcc1-50c8763d2fb0","html_url":"https://github.com/aastroza/modal-outlines-examples","commit_stats":null,"previous_names":["aastroza/modal-outlines-examples"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastroza%2Fmodal-outlines-examples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastroza%2Fmodal-outlines-examples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastroza%2Fmodal-outlines-examples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aastroza%2Fmodal-outlines-examples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aastroza","download_url":"https://codeload.github.com/aastroza/modal-outlines-examples/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241670156,"owners_count":20000327,"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":["cloud","generative-ai","gpu","json","llms","modal","outlines","serverless","structured-generation"],"created_at":"2024-11-14T07:20:22.766Z","updated_at":"2026-06-08T16:03:24.690Z","avatar_url":"https://github.com/aastroza.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# modal-outlines-examples\n\nExamples of code that use [Outlines](https://github.com/outlines-dev/outlines) to enable structured text generation for LLMs running on [Modal](https://modal.com).\n\nIs your computer only capable of running small, quantized LLMs? Would you love to have an **Nvidia H100** at home? Keep reading, because we're about to make your dream come true.\n\n## Level 1: The Basics\n\n**The basic idea:** We deploy a function to Modal, an easy-to-use cloud platform, then we call that function locally from a Jupyter notebook.\n\n**The unbelievable part:** The function will run on a super powerful GPU in the cloud. Plus, we get to use free processing credits ($30 monthly).\n\n\nGated repo: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2\n\n## Level 2: Different LLMs\n\nYeah, I know Mistral is good, but what if I want to test different models?\n\n## Level 3: vLLM\n\nComing [soon](https://github.com/vllm-project/vllm/pull/4109).\n\n## Level 4: FastAPI\n\nHow to serve an inference endpoint for structured text generation. GPU-powered. Serverless. Automatically scales. Pay as you go.\n\n## Installation\n\n```shell\nconda create --name modal-outlines-examples -c conda-forge python=3.11\nconda activate modal-outlines-examples\npip install -r requirements.txt\npython -m modal setup\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faastroza%2Fmodal-outlines-examples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faastroza%2Fmodal-outlines-examples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faastroza%2Fmodal-outlines-examples/lists"}