{"data":{"node":{"slug":"next-gpt-next-gpt","name":"NExT-GPT","tagline":"Code and models for ICML 2024 paper on multimodal large language model","github_url":"https://github.com/NExT-GPT/NExT-GPT","owner":"NExT-GPT","repo":"NExT-GPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/143576855?v=4","primary_language":"Python","stars":3637,"forks":359,"topics":["chatgpt","foundation-models","gpt-4","instruction-tuning","large-language-models","llm","mllm","multi-modal-chatgpt","multimodal","visual-language-learning"],"archived":false,"github_pushed_at":"2025-05-13T09:57:47+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/next-gpt-next-gpt","markdown_url":"https://www.graphcanon.com/tools/next-gpt-next-gpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/next-gpt-next-gpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=next-gpt-next-gpt"},"categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"chatgpt","name":"chatgpt"},{"slug":"foundation-models","name":"foundation-models"},{"slug":"instruction-tuning","name":"instruction-tuning"},{"slug":"large-language-models","name":"large language models"},{"slug":"llm","name":"llm"},{"slug":"multimodal","name":"multimodal"},{"slug":"visual-language-learning","name":"visual-language-learning"}],"edges":[{"type":"related","direction":"out","explanation":"NExT-GPT is a multimodal large language model and may be highlighted in the curated list of resources for Multimodal Large Language Models.","successor_context":null,"tool":{"slug":"bradyfu-awesome-multimodal-large-language-models","name":"Awesome-Multimodal-Large-Language-Models","tagline":"Latest Advances on Multimodal Large Language Models","github_url":"https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models","owner":"BradyFU","repo":"Awesome-Multimodal-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/54254631?v=4","primary_language":null,"stars":17978,"forks":1133,"topics":["chain-of-thought","in-context-learning","instruction-following","instruction-tuning","large-language-models","large-vision-language-model","large-vision-language-models","multi-modality","multimodal-chain-of-thought","multimodal-in-context-learning","multimodal-instruction-tuning","multimodal-large-language-models","visual-instruction-tuning"],"archived":false,"github_pushed_at":"2026-08-14T17:17:50+00:00","maintenance_label":"Very active","stars_delta_30d":29,"url":"https://www.graphcanon.com/tools/bradyfu-awesome-multimodal-large-language-models","markdown_url":"https://www.graphcanon.com/tools/bradyfu-awesome-multimodal-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bradyfu-awesome-multimodal-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bradyfu-awesome-multimodal-large-language-models"}},{"type":"integrates_with","direction":"out","explanation":"NExT-GPT can be evaluated using lmms-eval, which is a unified evaluation toolkit for multimodal large language models.","successor_context":null,"tool":{"slug":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Active","stars_delta_30d":52,"url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval"}},{"type":"integrates_with","direction":"out","explanation":"PaddleOCR could be used within NExT-GPT to preprocess text-based images as it supports multimodal inputs including visual data.","successor_context":null,"tool":{"slug":"paddlepaddle-paddleocr","name":"PaddleOCR","tagline":"A powerful, lightweight OCR toolkit to convert images and PDFs into structured data","github_url":"https://github.com/PaddlePaddle/PaddleOCR","owner":"PaddlePaddle","repo":"PaddleOCR","owner_avatar_url":"https://avatars.githubusercontent.com/u/23534030?v=4","primary_language":"Python","stars":87808,"forks":11187,"topics":["ai4science","chineseocr","document-parsing","document-translation","kie","ocr","paddleocr-vl","pdf-extractor-rag","pdf-parser","pdf2markdown","pp-ocr","pp-structure","rag"],"archived":false,"github_pushed_at":"2026-07-22T11:59:34+00:00","maintenance_label":"Active","stars_delta_30d":2062,"url":"https://www.graphcanon.com/tools/paddlepaddle-paddleocr","markdown_url":"https://www.graphcanon.com/tools/paddlepaddle-paddleocr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/paddlepaddle-paddleocr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=paddlepaddle-paddleocr"}},{"type":"integrates_with","direction":"out","explanation":"NExT-GPT can leverage Hugging Face's transformers for model training and inference since it deals with multimodal large language models.","successor_context":null,"tool":{"slug":"huggingface-transformers","name":"transformers","tagline":"Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models","github_url":"https://github.com/huggingface/transformers","owner":"huggingface","repo":"transformers","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":164121,"forks":34249,"topics":["audio","deep-learning","deepseek","gemma","glm","hacktoberfest","llm","machine-learning","model-hub","natural-language-processing","nlp","pretrained-models","python","pytorch","pytorch-transformers","qwen","speech-recognition","transformer","vlm"],"archived":false,"github_pushed_at":"2026-08-15T22:28:12+00:00","maintenance_label":"Very active","stars_delta_30d":1457,"url":"https://www.graphcanon.com/tools/huggingface-transformers","markdown_url":"https://www.graphcanon.com/tools/huggingface-transformers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-transformers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-transformers"}},{"type":"related","direction":"out","explanation":"Both platforms can be used for educational purposes and personalized learning through AI interaction but are focused on different aspects of AI engagement.","successor_context":null,"tool":{"slug":"jushbjj-mr-ranedeer-ai-tutor","name":"Mr.-Ranedeer-AI-Tutor","tagline":"A GPT-4 AI Tutor Prompt for customizable personalized learning experiences","github_url":"https://github.com/JushBJJ/Mr.-Ranedeer-AI-Tutor","owner":"JushBJJ","repo":"Mr.-Ranedeer-AI-Tutor","owner_avatar_url":"https://avatars.githubusercontent.com/u/36951064?v=4","primary_language":null,"stars":29599,"forks":3287,"topics":["ai","education","gpt-4","llm"],"archived":false,"github_pushed_at":"2025-09-30T08:08:00+00:00","maintenance_label":"Slowing","stars_delta_30d":-12,"url":"https://www.graphcanon.com/tools/jushbjj-mr-ranedeer-ai-tutor","markdown_url":"https://www.graphcanon.com/tools/jushbjj-mr-ranedeer-ai-tutor.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jushbjj-mr-ranedeer-ai-tutor","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jushbjj-mr-ranedeer-ai-tutor"}},{"type":"related","direction":"out","explanation":"NExT-GPT and litGPT both focus on advanced LLM capabilities but with a distinct emphasis on multimodality, making them related tools rather than direct integrations or dependencies.","successor_context":null,"tool":{"slug":"lightning-ai-litgpt","name":"litgpt","tagline":"High-performance LLMs with recipes for pretraining, finetuning and deployment","github_url":"https://github.com/Lightning-AI/litgpt","owner":"Lightning-AI","repo":"litgpt","owner_avatar_url":"https://avatars.githubusercontent.com/u/58386951?v=4","primary_language":"Python","stars":13605,"forks":1483,"topics":["ai","artificial-intelligence","deep-learning","large-language-models","llm","llm-inference","llms"],"archived":false,"github_pushed_at":"2026-07-20T10:24:12+00:00","maintenance_label":"Active","stars_delta_30d":137,"url":"https://www.graphcanon.com/tools/lightning-ai-litgpt","markdown_url":"https://www.graphcanon.com/tools/lightning-ai-litgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lightning-ai-litgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lightning-ai-litgpt"}},{"type":"integrates_with","direction":"out","explanation":"LlamaFactory is a framework designed to efficiently fine-tune LLMs and VLMs which complements NExT-GPT’s multimodal approach.","successor_context":null,"tool":{"slug":"hiyouga-llamafactory","name":"LlamaFactory","tagline":"Unified Efficient Fine-Tuning of 100+ LLMs & VLMs","github_url":"https://github.com/hiyouga/LlamaFactory","owner":"hiyouga","repo":"LlamaFactory","owner_avatar_url":"https://avatars.githubusercontent.com/u/16256802?v=4","primary_language":"Python","stars":74132,"forks":9071,"topics":["agent","ai","deepseek","fine-tuning","gemma","gpt","instruction-tuning","large-language-models","llama","llama3","llm","lora","moe","nlp","peft","qlora","quantization","qwen","rlhf","transformers"],"archived":false,"github_pushed_at":"2026-08-13T12:45:56+00:00","maintenance_label":"Very active","stars_delta_30d":803,"url":"https://www.graphcanon.com/tools/hiyouga-llamafactory","markdown_url":"https://www.graphcanon.com/tools/hiyouga-llamafactory.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hiyouga-llamafactory","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hiyouga-llamafactory"}},{"type":"related","direction":"out","explanation":null,"successor_context":null,"tool":{"slug":"shubhamsaboo-awesome-llm-apps","name":"awesome-llm-apps","tagline":"Over 100 runnable AI Agent and RAG apps to clone, tweak, and deploy.","github_url":"https://github.com/Shubhamsaboo/awesome-llm-apps","owner":"Shubhamsaboo","repo":"awesome-llm-apps","owner_avatar_url":"https://avatars.githubusercontent.com/u/31396011?v=4","primary_language":"Python","stars":131230,"forks":19346,"topics":["agents","llms","python","rag"],"archived":false,"github_pushed_at":"2026-08-03T03:30:58+00:00","maintenance_label":"Very active","stars_delta_30d":14464,"url":"https://www.graphcanon.com/tools/shubhamsaboo-awesome-llm-apps","markdown_url":"https://www.graphcanon.com/tools/shubhamsaboo-awesome-llm-apps.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/shubhamsaboo-awesome-llm-apps","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=shubhamsaboo-awesome-llm-apps"}}],"neighbours":[{"slug":"handsonllm-hands-on-large-language-models","name":"Hands-On-Large-Language-Models","tagline":"Official code repo for the O'Reilly Book - 'Hands-On Large Language Models'","github_url":"https://github.com/HandsOnLLM/Hands-On-Large-Language-Models","owner":"HandsOnLLM","repo":"Hands-On-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/174106807?v=4","primary_language":"Jupyter Notebook","stars":28252,"forks":6531,"topics":["artificial-intelligence","book","large-language-models","llm","llms","oreilly","oreilly-books"],"archived":false,"github_pushed_at":"2026-04-24T10:20:08+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/handsonllm-hands-on-large-language-models","markdown_url":"https://www.graphcanon.com/tools/handsonllm-hands-on-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/handsonllm-hands-on-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=handsonllm-hands-on-large-language-models","shared_categories":["model-training","llm-frameworks"]},{"slug":"bradyfu-awesome-multimodal-large-language-models","name":"Awesome-Multimodal-Large-Language-Models","tagline":"Latest Advances on Multimodal Large Language Models","github_url":"https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models","owner":"BradyFU","repo":"Awesome-Multimodal-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/54254631?v=4","primary_language":null,"stars":17978,"forks":1133,"topics":["chain-of-thought","in-context-learning","instruction-following","instruction-tuning","large-language-models","large-vision-language-model","large-vision-language-models","multi-modality","multimodal-chain-of-thought","multimodal-in-context-learning","multimodal-instruction-tuning","multimodal-large-language-models","visual-instruction-tuning"],"archived":false,"github_pushed_at":"2026-08-14T17:17:50+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/bradyfu-awesome-multimodal-large-language-models","markdown_url":"https://www.graphcanon.com/tools/bradyfu-awesome-multimodal-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bradyfu-awesome-multimodal-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bradyfu-awesome-multimodal-large-language-models","shared_categories":["llm-frameworks"]},{"slug":"nvidia-deeplearningexamples","name":"DeepLearningExamples","tagline":"State-of-the-Art Deep Learning scripts for various applications","github_url":"https://github.com/NVIDIA/DeepLearningExamples","owner":"NVIDIA","repo":"DeepLearningExamples","owner_avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","primary_language":"Jupyter Notebook","stars":14844,"forks":3408,"topics":["computer-vision","deep-learning","drug-discovery","forecasting","large-language-models","mxnet","nlp","paddlepaddle","pytorch","recommender-systems","speech-recognition","speech-synthesis","tensorflow","tensorflow2","translation"],"archived":false,"github_pushed_at":"2024-08-12T14:01:29+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/nvidia-deeplearningexamples","markdown_url":"https://www.graphcanon.com/tools/nvidia-deeplearningexamples.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-deeplearningexamples","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-deeplearningexamples","shared_categories":["model-training"]},{"slug":"lightning-ai-litgpt","name":"litgpt","tagline":"High-performance LLMs with recipes for pretraining, finetuning and deployment","github_url":"https://github.com/Lightning-AI/litgpt","owner":"Lightning-AI","repo":"litgpt","owner_avatar_url":"https://avatars.githubusercontent.com/u/58386951?v=4","primary_language":"Python","stars":13605,"forks":1483,"topics":["ai","artificial-intelligence","deep-learning","large-language-models","llm","llm-inference","llms"],"archived":false,"github_pushed_at":"2026-07-20T10:24:12+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/lightning-ai-litgpt","markdown_url":"https://www.graphcanon.com/tools/lightning-ai-litgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lightning-ai-litgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lightning-ai-litgpt","shared_categories":["model-training","llm-frameworks"]},{"slug":"oumi-ai-oumi","name":"oumi","tagline":"Easily fine-tune, evaluate and deploy open source LLMs/VLMs","github_url":"https://github.com/oumi-ai/oumi","owner":"oumi-ai","repo":"oumi","owner_avatar_url":"https://avatars.githubusercontent.com/u/167452922?v=4","primary_language":"Python","stars":9359,"forks":780,"topics":["dpo","evaluation","fine-tuning","gpt-oss","gpt-oss-120b","gpt-oss-20b","inference","llama","llms","sft","slms","vlms"],"archived":false,"github_pushed_at":"2026-07-24T05:44:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/oumi-ai-oumi","markdown_url":"https://www.graphcanon.com/tools/oumi-ai-oumi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/oumi-ai-oumi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=oumi-ai-oumi","shared_categories":["model-training"]},{"slug":"fareedkhan-dev-train-llm-from-scratch","name":"train-llm-from-scratch","tagline":"A straightforward method for training your LLM from raw text to aligned model generation","github_url":"https://github.com/FareedKhan-dev/train-llm-from-scratch","owner":"FareedKhan-dev","repo":"train-llm-from-scratch","owner_avatar_url":"https://avatars.githubusercontent.com/u/63067900?v=4","primary_language":"Python","stars":9141,"forks":1264,"topics":["gemini","large-language-models","llm","openai","training","transformers"],"archived":false,"github_pushed_at":"2026-08-17T05:07:26+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/fareedkhan-dev-train-llm-from-scratch","markdown_url":"https://www.graphcanon.com/tools/fareedkhan-dev-train-llm-from-scratch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fareedkhan-dev-train-llm-from-scratch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fareedkhan-dev-train-llm-from-scratch","shared_categories":["model-training"]},{"slug":"zai-org-codegeex","name":"CodeGeeX","tagline":"CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch.","github_url":"https://github.com/zai-org/CodeGeeX","owner":"zai-org","repo":"CodeGeeX","owner_avatar_url":"https://avatars.githubusercontent.com/u/223098841?v=4","primary_language":"Python","stars":8809,"forks":688,"topics":["code-generation","pretrained-models","tools"],"archived":false,"github_pushed_at":"2024-08-13T05:59:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/zai-org-codegeex","markdown_url":"https://www.graphcanon.com/tools/zai-org-codegeex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zai-org-codegeex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zai-org-codegeex","shared_categories":["model-training","llm-frameworks"]},{"slug":"eleutherai-gpt-neox","name":"gpt-neox","tagline":"Implementation of model parallel autoregressive transformers on GPUs based on Megatron and DeepSpeed libraries","github_url":"https://github.com/EleutherAI/gpt-neox","owner":"EleutherAI","repo":"gpt-neox","owner_avatar_url":"https://avatars.githubusercontent.com/u/68924597?v=4","primary_language":"Python","stars":7452,"forks":1119,"topics":["deepspeed-library","gpt-3","language-model","transformers"],"archived":false,"github_pushed_at":"2026-06-11T19:25:44+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/eleutherai-gpt-neox","markdown_url":"https://www.graphcanon.com/tools/eleutherai-gpt-neox.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eleutherai-gpt-neox","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eleutherai-gpt-neox","shared_categories":["model-training","llm-frameworks"]},{"slug":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval","shared_categories":[]},{"slug":"nvidia-generativeaiexamples","name":"GenerativeAIExamples","tagline":"Generative AI reference workflows for accelerated infrastructure and microservice architecture","github_url":"https://github.com/NVIDIA/GenerativeAIExamples","owner":"NVIDIA","repo":"GenerativeAIExamples","owner_avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","primary_language":"Jupyter Notebook","stars":4149,"forks":1095,"topics":["gpu-acceleration","large-language-models","llm","llm-inference","microservice","nemo","rag","retrieval-augmented-generation","tensorrt","triton-inference-server"],"archived":false,"github_pushed_at":"2026-08-05T16:54:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/nvidia-generativeaiexamples","markdown_url":"https://www.graphcanon.com/tools/nvidia-generativeaiexamples.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-generativeaiexamples","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-generativeaiexamples","shared_categories":["llm-frameworks"]},{"slug":"jia-lab-research-mgm","name":"MGM","tagline":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","github_url":"https://github.com/JIA-Lab-research/MGM","owner":"JIA-Lab-research","repo":"MGM","owner_avatar_url":"https://avatars.githubusercontent.com/u/64006090?v=4","primary_language":"Python","stars":3331,"forks":276,"topics":["generation","large-language-models","vision-language-model"],"archived":false,"github_pushed_at":"2024-05-04T14:36:51+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jia-lab-research-mgm","markdown_url":"https://www.graphcanon.com/tools/jia-lab-research-mgm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jia-lab-research-mgm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jia-lab-research-mgm","shared_categories":["model-training","llm-frameworks"]},{"slug":"roboflow-maestro","name":"maestro","tagline":"Streamlines fine-tuning for multimodal models PaliGemma 2, Florence-2, Qwen2.5-VL","github_url":"https://github.com/roboflow/maestro","owner":"roboflow","repo":"maestro","owner_avatar_url":"https://avatars.githubusercontent.com/u/53104118?v=4","primary_language":"Python","stars":2687,"forks":222,"topics":["captioning","fine-tuning","florence-2","multimodal","objectdetection","paligemma","phi-3-vision","qwen2-vl","transformers","vision-and-language","vqa"],"archived":false,"github_pushed_at":"2026-07-20T17:45:05+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/roboflow-maestro","markdown_url":"https://www.graphcanon.com/tools/roboflow-maestro.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/roboflow-maestro","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=roboflow-maestro","shared_categories":["model-training"]}]}}