5 مستودعات
Awesome GitHub RepositoriesTraining Frameworks
Open-source frameworks for training and fine-tuning small vision-language models from scratch or from pretrained components.
Distinct from Vision-Language Training: Distinct from Vision-Language Training: specifically provides a framework for training and fine-tuning, not just the training workflow itself.
Explore 5 awesome GitHub repositories matching artificial intelligence & ml · Training Frameworks. Refine with filters or upvote what's useful.
Awesome Training Frameworks GitHub Repositories
اعثر على أفضل المستودعات باستخدام الذكاء الاصطناعي.سنبحث عن أفضل المستودعات المطابقة باستخدام الذكاء الاصطناعي.
- jingyaogong/minimind-v
jingyaogong/minimind-v
6,431عرض على GitHubProvides an open-source framework for building and fine-tuning small vision-language models.
Pythonartificial-intelligencechatgptvision-language-model - salesforce/blip
salesforce/BLIP
5,676عرض على GitHubBLIP is a vision-language model framework that combines contrastive, matching, and language modeling objectives to align images with text. Built on a multimodal encoder-decoder architecture, it supports distributed data-parallel training with cosine learning rate scheduling and sliding-window metric tracking for training stability. The framework provides capabilities for image captioning, visual question answering, and cross-modal retrieval, scoring semantic alignment between images and text through learned embeddings. It includes toolkits for fine-tuning pre-trained models on custom datasets
Provides an open-source framework for training, fine-tuning, and evaluating vision-language models on custom image-text datasets.
Jupyter Notebookimage-captioningimage-text-retrievalvision-and-language-pre-training - huggingface/nanovlm
huggingface/nanoVLM
4,917عرض على GitHubnanoVLM is a training framework and toolkit for small vision-language models. It provides a PyTorch-based environment for training and fine-tuning models to associate image inputs with textual descriptions and generate natural language answers. The project includes a cloud model versioning tool for saving and loading model weights to centralized repositories to synchronize assets across environments. It also features a dedicated evaluation suite for measuring the accuracy and reliability of vision-language models against standard task datasets. The framework covers GPU resource planning thro
Provides a comprehensive framework for training and fine-tuning small vision-language models.
Python - mlfoundations/open_flamingo
mlfoundations/open_flamingo
4,107عرض على GitHubOpen Flamingo هو إطار عمل لتدريب النماذج اللغوية الكبيرة متعددة الوسائط مصمم لدمج مشفرات الرؤية المدربة مسبقاً مع النماذج اللغوية. ينفذ بنية رؤية-لغة تستخدم طبقات الانتباه المتقاطع (cross-attention) لمعالجة تسلسلات متداخلة من الصور والنصوص. يتميز النظام بقدرات التعلم متعدد الوسائط بلقطات قليلة (few-shot)، مما يسمح للنموذج بالتكيف مع مهام بصرية جديدة باستخدام مجموعة صغيرة من أمثلة الصور والنصوص المقدمة في المطالبة. ويدعم التعلم في السياق وتوليد النصوص متعدد الوسائط لمهام مثل الإجابة على الأسئلة البصرية والتعليق. يتضمن إطار العمل مدرب نموذج موزع يستخدم توازي البيانات ونقاط فحص التدرج (gradient checkpointing) لتحسين الذاكرة عبر وحدات معالجة رسومات متعددة. كما يوفر أدوات لتحميل مجموعات البيانات متعددة الوسائط المجزأة، وتقييم النموذج المتوازي، وبنية تحتية لاستضافة نماذج واسعة النطاق للاستدلال.
Offers a framework for training and deploying large-scale models that process interleaved sequences of images and text.
Pythoncomputer-visiondeep-learningflamingo - evolvinglmms-lab/otter
EvolvingLMMs-Lab/Otter
3,331عرض على GitHubOtter is a framework and toolkit for the pretraining, fine-tuning, and evaluation of vision-language models. It provides a pipeline for training large language models to process high-resolution images and video frames, integrating visual encoders with textual token spaces. The system is designed for multi-visual input processing, allowing models to interpret multiple images or video sequences within a single prompt. It supports multi-round conversation management to maintain context across interactions for detailed scene comprehension and visual reasoning. The framework covers a full develop
Provides a comprehensive framework for pretraining and fine-tuning vision-language models to process high-resolution images and video.
Pythonartificial-inteligencechatgptdeep-learning
