Vicuna
A LLaMA-based research chatbot trained on user-shared conversations to handle multi-turn dialogue.
A LLaMA-based research chatbot trained on user-shared conversations to handle multi-turn dialogue.
Discover sensitive data, monitor access, and enforce least privilege across clouds, SaaS, and AI applications.
Deploy and monitor enterprise LLM apps with managed compute, traffic routing, and access controls.
Open-source LLM evaluation and security testing for AI applications, agents, and workflows.
Licensed, structured 3D datasets for generating labeled AI training data
Manage and verify AI models, run them offline on a CPU, and serve responses locally.
Build and share generative AI apps using model chaining and your own data
Build, deploy, and govern enterprise AI agents on private infrastructure with no-code, visual, and code-based tools.
AI coding models for instruction-based code generation and single-line or multiline autocomplete.
Manage devices, model sessions, group policies and sensitive-content approvals across a private mesh.
Vector, text and structured search with machine-learned ranking for search, RAG and recommendation applications.
The supplied page describes NVIDIA tools for generating synthetic data for AI agents and language models.
Build language model workflows visually and extend them with sandboxed WebAssembly plugins.
AI ontology infrastructure for enterprise knowledge discovery, source tracing, and permission-controlled answers.
A cross-platform tensor library for running large machine learning models on commodity hardware.
Explore NVIDIA AI models, application blueprints, synthetic datasets, and DGX Spark playbooks.
Expert human data, real-world training environments, and contextual evaluations for AI models and agents.
Create retrieval plugins that let ChatGPT search and use your own text data.
Marvin turns unstructured input into Python values and runs language-model tasks with tools.
Cloud and AI inference cost management with pooled commitments, model routing, budgets, and spend reporting.
Google language model for multilingual text, reasoning and code generation
Ontology-powered knowledge graphs and traceable enterprise AI answers for business and technical teams.
Save tokens in AI chats and coding agents with prompt optimization, Smart Paste and repeat-file context reuse.
A playground page with documentation, provider navigation, history and browser-data recovery.
Evaluate pull request changes against team-approved criteria and preserve evidence for code review.
A programming language for LLM prompting with types, templates, constraints and Python control flow.
Open-source LLM customization with LoRA fine-tuning and perplexity evaluation examples.
Build, train and deploy specialized AI models with cloud GPUs, development Studios and enterprise infrastructure.
Build and share machine learning web interfaces in Python without writing frontend code.
Fine-tune domain-specific AI models with data labeling, synthetic training data, evaluation, and deployment tools.
Prompt management, LLM evaluations, and agent observability for engineering teams and domain experts.
Open-source AI agent monitoring with production tracing, failure detection, and coding-agent dispatch.
Build AI technical assistants that answer customer and employee questions from documentation and support resources.
LLM application development, management and evaluation platform now being sunset as its team joins Anthropic.
AI document extraction with structured outputs, source citations, and APIs for document workflows.
Pre-trained English embeddings and text classifiers for Node.js, with a focus on serverless cold-start performance.