Utilities intended for use with Llama models.

A Comprehensive Toolkit for High-Quality PDF Content Extraction

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

Explorations into some recent techniques surrounding speculative decoding

Simple Byte pair Encoding mechanism used for tokenization process . written purely in C

LLM101n: Let's build a Storyteller

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

Must-read Papers on LLM Agents.

A self-organizing file system with llama 3

The easiest way to use Agentic RAG in any enterprise

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

🐚 OpenDevin: Code Less, Make More

A list of LLMs Tools & Projects

A repo lists papers related to LLM based agent

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Neural Networks: Zero to Hero

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

Reconquer the canvas: beautiful Tikz figures without clunky Tikz code

my blog

Instant voice cloning by MyShell.

Examples in the MLX framework

Tensor library for machine learning

DSPy: The framework for programming—not prompting—foundation models

Python bindings for llama.cpp

The official Meta Llama 3 GitHub site

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

LLM training in simple, raw C/CUDA

C API for MLX

MLX: An array framework for Apple silicon