gante
Follow
Stars
A unified evaluation framework for large language models
PyTorch native quantization and sparsity for training and inference
Formatron empowers everyone to control the format of language models' output with minimal overhead.
Efficient and general syntactical decoding for Large Language Models
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
A modular graph-based Retrieval-Augmented Generation (RAG) system
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Large Action Model framework to develop AI Web Agents
A pytorch quantization backend for optimum
Representation Engineering: A Top-Down Approach to AI Transparency
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Minimalistic large language model 3D-parallelism training
🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers
Machine Learning Engineering Open Book
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Minimum Bayes Risk Decoding for Hugging Face Transformers
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Playing Pokemon Red with Reinforcement Learning
🇵🇹 List of technology companies in Portugal.
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads