Interactive visualizations of transformer model architectures
EleutherAI - Non-profit AI research lab focused on open-source LLMs
GPT - OpenAI's Generative Pre-trained Transformers
Llama - Meta's Large Language Model Meta AI
T5 - Google's Text-to-Text Transfer Transformer
Gemma - Google's lightweight open models built from Gemini research
Qwen - Alibaba Cloud's multilingual LLM series
Deepseek - Chinese AI lab known for efficient MoE architectures
Other Chinese/Asian AI Labs
Microsoft Phi - Small language models with strong reasoning
Allen AI OLMo - Fully open language models with training data/code
Mistral - French AI startup known for efficient open models (founded 2023)
Grok - xAI (Elon Musk's AI company)
Gigachat
📊 Statistics