{"id":19121833,"url":"https://github.com/promptslab/llmtuner","last_synced_at":"2025-07-26T12:38:40.922Z","repository":{"id":205351324,"uuid":"633855520","full_name":"promptslab/LLMtuner","owner":"promptslab","description":"FineTune LLMs in few lines of code (Text2Text, Text2Speech, Speech2Text)","archived":false,"fork":false,"pushed_at":"2024-01-13T10:32:58.000Z","size":605,"stargazers_count":237,"open_issues_count":3,"forks_count":15,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-09T19:19:11.176Z","etag":null,"topics":["fine-tuning","fine-tuning-llm","finetune","finetune-gpt","finetune-llama","finetune-llm","finetune-llms","finetune-whisper","finetunechatgpt","finetuning","finetuning-large-language-models","finetuning-rl","llm","llm-framework","llm-inference","llm-training","llmops","llmtuner","whisper","whisper-finetune"],"latest_commit_sha":null,"homepage":"","language":"Python","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/promptslab.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":"2023-04-28T12:44:42.000Z","updated_at":"2025-03-25T18:32:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"42566d04-c37f-43bf-a438-e795c0bb19bd","html_url":"https://github.com/promptslab/LLMtuner","commit_stats":null,"previous_names":["promptslab/llmtuner"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/promptslab%2FLLMtuner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/promptslab%2FLLMtuner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/promptslab%2FLLMtuner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/promptslab%2FLLMtuner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/promptslab","download_url":"https://codeload.github.com/promptslab/LLMtuner/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248094991,"owners_count":21046770,"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":["fine-tuning","fine-tuning-llm","finetune","finetune-gpt","finetune-llama","finetune-llm","finetune-llms","finetune-whisper","finetunechatgpt","finetuning","finetuning-large-language-models","finetuning-rl","llm","llm-framework","llm-inference","llm-training","llmops","llmtuner","whisper","whisper-finetune"],"created_at":"2024-11-09T05:18:40.827Z","updated_at":"2025-04-09T19:19:42.954Z","avatar_url":"https://github.com/promptslab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg width=\"220px\" src=\"https://raw.githubusercontent.com/promptslab/LLMTuner/main/assets/logo.png\"\u003e\n\u003ch1\u003eLLMTuner\u003c/h1\u003e\u003c/div\u003e\n\u003c!-- \n\u003ch2 align=\"center\"\u003eLLMTuner\u003c/h2\u003e --\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cp align=\"center\"\u003eLLMTuner: Fine-Tune Llama, Whisper, and other LLMs with best practices like LoRA, QLoRA, through a sleek, scikit-learn-inspired interface.\n\u003c/p\u003e\n\u003c/p\u003e\n\n \u003ch4 align=\"center\"\u003e\n  \u003ca href=\"https://github.com/promptslab/LLMTuner/blob/main/LICENSE\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/License-Apache_2.0-blue.svg\" alt=\"LLMTuner is released under the Apache 2.0 license.\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"http://makeapullrequest.com\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square\" alt=\"http://makeapullrequest.com\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://discord.gg/m88xfYMbK6\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Discord-Community-orange\" alt=\"Community\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://colab.research.google.com/drive/1ia9KvqEGOxARtJScPBY6ccF8l41-w_l5?usp=sharing\"\u003e\n    \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"colab\" /\u003e\n  \u003c/a\u003e\n\u003c/h4\u003e\n\n\n## Installation\n\n### With pip\n\nThis repository is tested on Python 3.7+\n\nYou should install Promptify using Pip command\n\n```bash\npip3 install git+https://github.com/promptslab/LLMTuner.git\n```\n\n## Quick tour\n\nTo finetune Large models, we provide the `Tuner` API.\n\n```python\n\nfrom llmtuner import Tuner, Dataset, Model, Deployment\n\n# Initialize the Whisper model with parameter-efficient fine-tuning\nmodel = Model(\"openai/whisper-small\", use_peft=True)\n\n# Create a dataset instance for the audio files\ndataset = Dataset('/path/to/audio_folder')\n\n# Set up the tuner with the model and dataset for fine-tuning\ntuner = Tuner(model, dataset)\n\n# Fine-tune the model\ntrained_model = tuner.fit()\n\n# Inference with Fine-tuned model\ntuner.inference('sample.wav')\n\n# Launch an interactive UI for the fine-tuned model\ntuner.launch_ui('Model Demo UI')\n\n# Set up deployment for the fine-tuned model\ndeploy = Deployment('aws')  # Options: 'fastapi', 'aws', 'gcp', etc.\n\n# Launch the model deployment\ndeploy.launch()\n\n```\n\n\u003ch2\u003eFeatures 🤖 \u003c/h2\u003e\n\u003cul\u003e\n  \u003cli\u003e\u003cstrong\u003e🏋️‍♂️ Effortless Fine-Tuning:\u003c/strong\u003e Finetune state-of-the-art LLMs like Whisper, Llama with minimal code\u003c/li\u003e\n  \u003cli\u003e\u003cstrong\u003e⚡️ Built-in utilities\u003c/strong\u003e for techniques like LoRA and QLoRA \u003c/li\u003e\n  \u003cli\u003e\u003cstrong\u003e⚡️ Interactive UI:\u003c/strong\u003e Launch webapp demos for your finetuned models with one click\u003c/li\u003e\n  \u003cli\u003e\u003cstrong\u003e🏎️ Simplified Inference:\u003c/strong\u003e Fast inference without separate code\u003c/li\u003e\n  \u003cli\u003e\u003cstrong\u003e🌐 Deployment Readiness:\u003c/strong\u003e (Coming Soon) Deploy your models with minimal effort to aws, gcp etc, ready to share with the world.\u003c/li\u003e\n\u003c/ul\u003e\n\n\n\n### Supported Models :\n\n| Task Name | Colab Notebook | Status |\n|-------------|-------|-------|\n| Fine-Tune Whisper | [Fine-Tune Whisper](https://colab.research.google.com/drive/1j_1AcPRk4s1uivVRSwrsOfodjPv55Jpc?usp=sharing) | ✅  |\n| Fine-Tune Whisper Quantized  | [LoRA](https://colab.research.google.com/drive/1ia9KvqEGOxARtJScPBY6ccF8l41-w_l5?usp=sharing) | ✅    |\n| Fine-Tune Llama | [Coming soon..](#) | ✅    |\n\n\n## Community \n\u003cdiv align=\"center\"\u003e\nIf you are interested in Fine-tuning Open source LLMs, Building scalable Large models, Prompt-Engineering, and other latest research discussions, please consider joining \u003ca href=\"https://discord.gg/m88xfYMbK6\"\u003ePromptsLab\u003c/a\u003e\u003c/div\u003e\n\u003cdiv align=\"center\"\u003e\n\u003cimg alt=\"Join us on Discord\" src=\"https://img.shields.io/discord/1069129502472556587?color=5865F2\u0026logo=discord\u0026logoColor=white\"\u003e\n\u003c/div\u003e\n\n```\n\n@misc{LLMtuner2023,\n  title = {LLMTuner: Fine-Tune Large Models with best practices through a sleek, scikit-learn-inspired interface.},\n  author = {Pal, Ankit},\n  year = {2023},\n  howpublished = {\\url{https://github.com/promptslab/LLMtuner}}\n}\n\n```\n\n## 💁 Contributing\n\nWe welcome any contributions to our open source project, including new features, improvements to infrastructure, and more comprehensive documentation. \nPlease see the [contributing guidelines](#)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpromptslab%2Fllmtuner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpromptslab%2Fllmtuner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpromptslab%2Fllmtuner/lists"}