7 Repos
Awesome GitHub RepositoriesGeneralization And Learning
Techniques for instruction tuning, in-context learning, and continual skill acquisition.
Explore 7 awesome GitHub repositories matching part of an awesome list · Generalization And Learning. Refine with filters or upvote what's useful.
Awesome Generalization And Learning GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- microsoft/unilm
microsoft/unilm
22,030Auf GitHub ansehenThis project is a comprehensive framework and toolkit for developing, optimizing, and deploying transformer-based models across multimodal, document intelligence, and natural language processing tasks. It provides a unified neural architecture that processes text, vision, audio, and document layout data through a shared set of weights, enabling researchers and developers to build foundational models that align cross-modal representations. The platform distinguishes itself through advanced training and inference strategies designed for large-scale deep learning. It incorporates specialized mec
Neural codec models for zero-shot in-context learning.
Pythonbeitbeit-3bitnet - google-research/t5x
google-research/t5x
2,972Auf GitHub ansehenGo to T5X ReadTheDocs Documentation Page.
Scalable instruction-finetuning for diverse task performance.
Python - baaivision/painter
baaivision/Painter
2,594Auf GitHub ansehenPainter & SegGPT Series: Vision Foundation Models from BAAI
Generalist model for in-context visual learning tasks.
Pythoncvpr2023generalist-modelgeneralist-painter - thudm/agenttuning
THUDM/AgentTuning
1,499Auf GitHub ansehen🤗 Model (AgentLM-70B) • 🤗 Dataset (AgentInstruct) • 📃 Paper • 🌐 Project Page
Instruction tuning to enable generalized agent capabilities.
Python - woooodyy/agentgym
WooooDyy/AgentGym
Benchmark and environment for evolving agents across diverse tasks.
Pythonagentlarge-language-modelsllm - bigscience-workshop/t-zero
bigscience-workshop/t-zero
Multitask training for zero-shot task generalization.
- openlemur/lemur
OpenLemur/Lemur
Harmonizes natural language and code for improved agent generalization.
