Models

A Python library for training and evaluating knowledge graph embedding models, with dozens of built-in models and datasets and a high-level pipeline function for benchmarking a model on a dataset in a few lines of code.

• Models

A technique and library for distilling any sentence-transformer model into a small, fast static embedding model, cutting size by up to 50 times and inference time by up to 500 times for a small drop in accuracy.

• RAG
• Models

A Kubernetes-native platform for distributed AI model training and large language model fine-tuning, orchestrating multi-node, multi-GPU jobs across frameworks such as PyTorch, JAX, HuggingFace and Megatron-LM.

• Models
• Containers

An AutoML library in Scala that runs on Apache Spark, automating feature engineering and model selection to build strongly typed, production machine learning pipelines with close to hand-tuned accuracy.

• Models
• Data engineering

An extension of the veRL reinforcement-learning library for training large language and vision-language model agents, using a step-independent multi-turn rollout design that supports long-horizon, many-step tasks and a new algorithm called Group-in-Group Policy Optimization.

• Models

A modular, full-stack reinforcement learning library for training large language model and vision-language model agents, combining a training framework, a Tinker API backend, an agent layer for long-horizon tasks, and a gymnasium of tool-use environments.

• Models
• Inference

A collection of 419 pretrained AI models covering object detection, speech recognition, image generation, large language models and more, each runnable from the same simple command-line interface using the ailia SDK.

• Models

An AI model optimization toolkit for the ONNX Runtime that, given a model and target hardware, composes fine-tuning, conversion, quantization and other optimization techniques to produce the most efficient ONNX model for inference on CPUs, GPUs and NPUs.

• Models

A high-performance, open-source large language model library and reference implementation written in pure Python and JAX, aimed at training and fine-tuning models such as Gemma, Llama, DeepSeek, Qwen and Mistral at scale on Google Cloud TPUs and GPUs.

• Models

A JAX-based library for post-training large language models, providing efficient supervised fine-tuning, reinforcement learning and agentic reinforcement learning on TPUs.

• Models
• Inference

A roughly 0.1-billion-parameter end-to-end omni model, trained entirely from scratch, that takes text, speech, and image input and produces text and streaming speech output.

• Models
• Speech

A library for fine-tuning, evaluating, and running personalized, private open-source large language models locally or in a private cloud.

• Models
• Inference

A library that unifies training, inference, and evaluation of diffusion language models, aiming to make that pipeline transparent and reproducible.

• Models
• Inference

A tool from Roboflow that streamlines fine-tuning multimodal vision-language models such as Florence-2, PaliGemma 2, and Qwen2.5-VL.

• Models

An open-source library from Intel for quantizing and compressing deep-learning and large language models across PyTorch, TensorFlow, and ONNX Runtime.

• Models

A software toolkit from Qualcomm for quantizing and compressing trained neural network models to reduce their compute and memory footprint for edge deployment.

• Models

A reinforcement-learning framework for training multi-turn reasoning agents that also diagnoses failure modes such as reasoning collapse during training.

• Models

A code library for training and running vision-language document retrieval models such as ColPali, ColQwen2, and ColSmol that embed and search documents by their visual layout as well as their text.

• RAG
• Models

A library that adds parameter-efficient fine-tuning methods, such as LoRA and adapters, to more than 20 Hugging Face Transformers models with minimal extra code.

• Models

A minimalist library from Hugging Face for pretraining transformer language models with 3D parallelism across many GPUs.

• Models

A dynamic training framework, built on LLaMA-Factory, that schedules training data during large-language-model fine-tuning through data selection, mixture, and reweighting.

• Models

A general-purpose fine-tuning toolkit for image, video, and audio diffusion models, built for simplicity and easily understood code.

• Models
• Generative media

An implementation of a language model architecture that removes matrix multiplication operations, compatible with Hugging Face Transformers, with pretrained checkpoints from 370 million to 2.7 billion parameters.

• Models

A local demo application for running the Bonsai 2 27B language model, a heavily compressed reasoning model with vision and tool-calling support, on a laptop or single GPU.

• Models
• Inference