Stars
Emotive animated eyes on an OLED display, as inspired by Anki Cozmo etc.
KAG is a knowledge-enhanced generation framework based on OpenSPG engine, which is used to build knowledge-enhanced rigorous decision-making and information retrieval knowledge services
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
[ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?
A simple, easy-to-hack GraphRAG implementation
Zero shot vulnerability discovery using LLMs
Blazing fast whisper turbo for ASR (speech-to-text) tasks
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
MemFree - Hybrid AI Search Engine & AI Page Generator
Modeling, training, eval, and inference code for OLMo
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
Open-source evaluation toolkit of large vision-language models (LVLMs), support 160+ VLMs, 50+ benchmarks
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
[IROS 2024] Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation. [CoRL 2024] OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
Multilingual Voice Understanding Model
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
Mobile-Agent: The Powerful Mobile Device Operation Assistant Family
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Utilities intended for use with Llama models.
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…