toolhuggingfacedatasets🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation toolsData processingDatasetsGitHubApache 2.0
agenthuggingfacesmolagents🤗 smolagents: a barebones library for agents that think in code.AgentsTool useGitHubApache 2.0
evaluationpromptfoopromptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.EvaluationRed teamingGitHubMIT
researchJay Gala et al.IndicTrans2 research paperResearch paper describing IndicTrans2 and its translation resources. Read the original methodology and distinguish author-reported results from independent Suvyo evaluation.TranslationIndic languageIndian languagesarXivLicense unknown
modelQwenQwen3 Embedding 0.6BEmbedding checkpoint for retrieval experiments. Evaluate retrieval relevance on the documents and languages used by the application.Embeddings / feature extractionHugging FaceApache 2.0
modelQwenQwen2.5 Coder 1.5B InstructInstruction-tuned coding checkpoint for investigating code-focused tasks. Published capabilities are not independent Suvyo measurements.Text generationHugging FaceApache 2.0
modelQwenQwen3.5 0.8BCompact Qwen3.5 checkpoint. Inspect the model card, modalities and runtime compatibility before choosing an inference stack.Image and text understandingHugging FaceApache 2.0
modelQwenQwen3 1.7BText-generation checkpoint in the Qwen3 family. A candidate for controlled local inference and structured-output experiments.Text generationHugging FaceApache 2.0
modelQwenQwen3 0.6BCompact text-generation checkpoint for testing small-model workflows. Compare actual task accuracy and runtime costs before deployment.Text generationHugging FaceApache 2.0