Tag

ChatGPT helps you get answers, find inspiration and be more productive. It is free to use and easy to try. Just ask and ChatGPT can help with writing, learning, brainstorming and more.

Claude is a next generation AI assistant built by Anthropic and trained to be safe, accurate, and secure to help you do your best work. Create with Claude.

Gemini is your personal, proactive, and powerful AI assistant from Google. Try it for free to help with work, school, and at home for whatever inspires you.

Grok is a free AI assistant designed by xAI to maximize truth and objectivity. Grok offers real-time search, image generation, trend analysis, and more.

Provides official documentation for the Transformers library — APIs, model definitions, training (Trainer), inference pipelines, tokenizers, and integrations for text, vision, audio and multimodal models. Focused on developer workflows and production use.

xFormers is a modular, hackable, and efficiency-oriented Transformer building-blocks library from Facebook Research (Meta). It provides multiple attention implementations (memory-efficient exact attention, sparse and block-sparse attention), fused operators, and custom CUDA kernels to speed up transformer research and prototyping within the PyTorch ecosystem.

Transformer-based foundation model for tabular data that provides pre-trained checkpoints for fast classification and regression, with GPU-accelerated local inference and an optional cloud client. Best suited for small-to-medium datasets (~≤50k rows).

LLaVA is an open-source large language and vision assistant project that introduces visual instruction tuning to teach large language models to understand and follow multimodal (image+text) instructions. The repository includes papers, model checkpoints (Model Zoo), training and evaluation scripts, demos (Gradio), and tooling for fine-tuning, quantized inference, and deployment. LLaVA aims to bring LLM-level conversational capabilities to vision tasks and has continued evolving (LLaVA-1.5, LLaVA-NeXT, video/interactive variants).

Fine-tuning and deployment framework for LLMs and MLLMs — supports 600+ text and 400+ multimodal models, integrates PEFT/LoRA families, quantized training (BNB/AWQ/GPTQ/FP8), Megatron parallelism, and RL-based alignment workflows for end-to-end training, evaluation, and inference.

Chat with DeepSeek AI – your intelligent assistant for coding, content creation, file reading, and more. Upload documents, engage in long-context conversations, and get expert help in AI, natural language processing, and beyond.

A selective State Space Model architecture and PyTorch implementation for linear-time sequence modeling. Hardware-aware, designed for information-dense tasks (e.g. language modeling), with pretrained weights on Hugging Face; requires CUDA-enabled PyTorch.

torchtitan is a PyTorch-native platform for rapid experimentation and large-scale training of generative AI models. It provides multi-dimensional composable parallelisms (FSDP2, tensor/pipeline/context parallel), distributed checkpointing, float8 and MXFP8 support, torch.compile integration, and out-of-the-box support for training Llama 3.1 models. It targets both research and production-scale LLM pretraining.