benchmark and evaluate generative research synthesis

TAG-Bench: A benchmark for table-augmented generation (TAG)

Efficient and Scalable Estimation of Tool Representations in Vector Space

[EMNLP 2024 Main] Virtual Personas for Language Models via an Anthology of Backstories

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

The official repo for "LLoCo: Learning Long Contexts Offline"

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

An extremely fast Python linter and code formatter, written in Rust.

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!

FacTool: Factuality Detection in Generative AI

The implementation of DeBERTa

Port of OpenAI's Whisper model in C/C++

MLX: An array framework for Apple silicon

CoreNet: A library for training deep neural networks

SoTA LLM for converting natural language questions to SQL queries

The official Meta Llama 3 GitHub site

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

LLM inference in C/C++

A natural language interface for computers

Robust recipes to align language models with human and AI preferences

⚡ A Fast, Extensible Progress Bar for Python and CLI

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Mamba SSM architecture

🦜🔗 The platform for reliable agents.

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.