Models

A Python framework for computing, using and training embedding and reranking models, including sentence embeddings, cross-encoder reranking, sparse embeddings and ColBERT-style multi-vector retrieval, for semantic search and similarity tasks.

• RAG
• Models

A library for post-training foundation language models with reinforcement learning and preference optimization methods, such as supervised fine-tuning, GRPO and DPO, built on top of Hugging Face Transformers.

• Models

A framework for running and fine-tuning large language models through CPU-GPU heterogeneous computing, letting large mixture-of-experts models do inference and LoRA fine-tuning on consumer hardware with CPU expert offload.

• Models
• Inference

Two open-weight language models from OpenAI, gpt-oss-120b and gpt-oss-20b, designed for reasoning and agentic tasks such as function calling, web browsing and code execution, released under the Apache 2.0 license.

• Models

An open-source financial large language model project offering sentiment analysis, forecasting and other finance-specific model tooling, maintained by the AI4Finance Foundation.

• Models

A library of parameter-efficient fine-tuning methods, such as LoRA, that adapt large pretrained models to a task by training only a small number of extra parameters instead of the whole model.

• Models

A mobile app for running open-source generative AI models fully on-device, for exploring, trying and evaluating on-device LLMs and other generative AI features offline.

• Models
• Inference

A PyTorch implementation of the Vision Transformer (ViT) for image classification, plus many published variants and extensions of the architecture.

• Models

A document-parsing OCR model from Baidu built for one-shot, long-horizon parsing, with inference support through Transformers, vLLM and SGLang.

• Models

An open effort to reproduce DeepSeek-R1, providing scripts to train reasoning models with SFT and GRPO, generate synthetic training data, and evaluate the results.

• Models

A multilingual, non-autoregressive decision engine that returns typed choice, score and yes/no judgments over text in a single forward pass, across more than 100 languages, with automatic routing to the right checkpoint.

• Models

An array framework for machine learning on Apple silicon, with a NumPy-like Python API and matching C++, C and Swift APIs, plus higher-level packages that follow PyTorch.

• Models

A cross-platform framework for building customizable on-device machine learning pipelines for vision, audio and text, deployable to mobile, web, desktop and edge devices.

• Models
• Inference

A deep learning training system for large AI models that combines data, pipeline, tensor and ZeRO-style parallelism so a model can be split and trained across many GPUs at lower cost.

• Models

A deep learning optimization library for distributed training and inference of large models, providing memory- and compute-efficient parallelism techniques such as ZeRO and 3D parallelism.

• Models
• Inference

Ray is a unified Python framework for scaling AI and general compute workloads from a laptop to a cluster, pairing a distributed runtime core with a set of AI libraries.

• Models
• Data engineering

Ultralytics YOLOv5 is a PyTorch-based computer-vision model for object detection, instance segmentation and image classification, mature and widely deployed after years of production use.

• Models

MiniMind is a from-scratch project and tutorial for training a roughly 64-million-parameter language model in about two hours on a single consumer GPU, without relying on high-level training-library abstractions.

• Models
• Tutorials

LlamaFactory is a zero-code CLI and web UI for fine-tuning more than a hundred open large language and vision-language models, from LoRA adapters through full-parameter training.

• Models

Unsloth is a desktop application and toolkit for running and fine-tuning large language and diffusion models locally, supporting formats such as GGUF and MLX across NVIDIA, AMD and Intel GPUs as well as CPUs.

• Models
• Inference

Hugging Face's Python library of model definitions for text, vision, audio and multimodal machine learning, used for both inference and training.

• Models
• Inference