Обзор
Просматривайте все технологии графа по типу и категории.
По типу
По категории
- Алгоритмы 30
- Модели 16
- Модели эмбеддингов 8
- Методы 35
- Промптинг 10
- Фреймворки 12
- Фреймворки LLM 6
- Базы данных 3
- Векторные базы данных 8
- Поисковые движки 4
- Инфраструктура 15
- MLOps 4
- Оценка 6
- Оборудование 11
- Безопасность и выравнивание 6
- Приложения 7
- Мультимодальные 5
- ИИ-агенты 4
- Бенчмарки 11
- Наборы данных 7
15 technologies shown
- LangChain framework Framework for composing language models with retrieval, tools and memory.
- LlamaIndex framework Data framework focused on ingesting, indexing and querying private knowledge.
- PyTorch framework The dominant deep learning framework, built around dynamic computation graphs.
- TensorFlow framework Google's deep learning framework, oriented toward deployment at scale.
- Sentence Transformers framework Library for embedding sentences and passages into vectors.
- Keras framework High-level modelling API that runs on several backends.
- Ray framework Distributed execution framework for scaling Python workloads.
- DSPy framework Builds model pipelines as programs whose prompts are optimised rather than written.
- DeepSpeed framework Training optimisation library for large models across many GPUs.
- AutoGen framework Framework for multi-agent conversations where agents critique each other.
- JAX framework NumPy-like array library with automatic differentiation and XLA compilation.
- Unsloth framework Fine-tuning implementation with hand-written kernels for speed and low memory.
- CrewAI framework Defines agent teams with roles and tasks, and runs them in order.
- Haystack framework Framework for building retrieval and question-answering pipelines.
- Axolotl framework Configuration-driven fine-tuning runner for many model architectures.