BICLab/SpikingBrain-7B

brain-inspired language model with spiking neurons, efficient attention, and MoE modules for ultra-long context processing

View on index · View in 3D Map

Related repos

• Framework for language agents with cognitive architectures
• efficient attention for long-context LLMs
• PyTorch toolkit for conversational AI
• Synthesizes speech without tokenizers
• AI chat app with branching conversations, file uploads, plugin support, and local model options
• Builds voice agents for phone calls with FastRTC and Twilio
• Data analysis platform using large language models
• parallel training for language models with dataset prep and programmatic access
• open-source language and vision models with huge context window and hybrid attention
• Muon optimizer for training large language models