Stars
Textbook on reinforcement learning from human feedback
Snips Python library to extract meaning from text
Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications.
Fully open reproduction of DeepSeek-R1
Audio Dataset for training CLAP and other models
Implementation of all RAG techniques in a simpler way
Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. 👨🏻🍳
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
LLMCompiler is an Agent Architecture designed to speed up the execution of agent tasks by executing them quickly in the DAG. It also saves the cost of redundant token use by reducing the number of …
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
A Comprehensive Toolkit for High-Quality PDF Content Extraction
Python library for loading and using triangular meshes.
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".
aider is AI pair programming in your terminal
Large Concept Models: Language modeling in a sentence representation space
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.