dhara-chat
🌊
1
ZeroGPU demo of dhara-250M tri-mode (AR/diffusion/self-spec)
Dhara Foundational Models
Diffusion Language Models combining deep narrow networks, Canon layers (depthwise causal convolutions), and WSD (Warmup-Stable-Decay) training.
Diffusion Language Models combining deep narrow networks, Canon layers (depthwise causal convolutions), and WSD (Warmup-Stable-Decay) training.
ZeroGPU demo of dhara-250M tri-mode (AR/diffusion/self-spec)
