MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

C++ Client Libraries for Google Cloud Services

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

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

Hackable and optimized Transformers building blocks, supporting a composable construction.

QLoRA: Efficient Finetuning of Quantized LLMs

A fast, responsive, multipurpose and feature-rich Hugo theme.

Lexbor is development of an open source HTML Renderer library. https://lexbor.com

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Code for CRATE (Coding RAte reduction TransformEr).

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.

Example pybind11 module built with a Python-based build system

An example combining scikit-build and pybind11

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Seamless operability between C++11 and Python

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

Reference implementation for DPO (Direct Preference Optimization)

C++ Library Manager for Windows, Linux, and MacOS

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

AI generated UI components

Robust Speech Recognition via Large-Scale Weak Supervision

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Home of StarCoder: fine-tuning & inference!

DSPy: The framework for programming with foundation models

A real world full-stack application using LlamaIndex

Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything