Agentic components of the Llama Stack APIs

A new benchmark for measuring LLM's capability to detect bugs in large codebase.

Language model alignment-focused deep learning curriculum

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

A library for mechanistic interpretability of GPT-style language models

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

An Extensible Deep Learning Library

LLM101n: Let's build a Storyteller

A high-throughput and memory-efficient inference and serving engine for LLMs

Make huge neural nets fit in memory

A programming framework for agentic AI 🤖

Deep Learning Fundamentals -- Code material and exercises

Construct a modern data stack and orchestration the workflows to create high quality data for analytics and ML applications.

Distributed training (multi-node) of a Transformer model

Classical equations and diagrams in machine learning

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

A pre-commit hook for Ruff.

🐍💯pySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box.

A simple jailbreak detection tool for safeguarding LLMs.

A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

Blazingly fast cleaning swear words (and their leetspeak) in strings

A realtime serving engine for Data-Intensive Generative AI Applications

Analyzing and scoring reasoning traces of LLMs

Google Drive Public File Downloader when Curl/Wget Fails