Muse2-125M
Muse2-125M — это младший брат Muse2-230M — та же самая гибридная архитектура свертки/внимания, разработанная с нуля и рассчитанная...
Muse2-125M — это младший брат Muse2-230M — та же самая гибридная архитектура свертки/внимания, разработанная с нуля и рассчитанная...
«S1-mini» by «Superwhisper» — superwhisper/s1-mini converted to the LiteRT-LM (.litertlm) format for on-device inference with Google’s LiteRT-LM runtime....
LiteRT is Google’s on-device runtime, the new name for TensorFlow Lite (Android: com.google.ai.edge.litert:litert), and litert-torch, the renamed ai-edge-torch,...
LFM2.5-2.6B is a compact multilingual model built on LiquidAI’s hybrid architecture, combining convolutional and attention layers for efficient...
LFM2.5-2.6B is a compact multilingual model built on LiquidAI’s hybrid architecture, combining convolutional and attention layers for efficient...
LFM2.5-2.6B is a compact multilingual model built on LiquidAI’s hybrid architecture, combining convolutional and attention layers for efficient...
> [!TIP] > This model is reproducible! > > See the README in the reproduce directory for more...
> [!TIP] > This model is reproducible! > > See the README in the reproduce directory for more...
This model was converted to MLX format from LiquidAI/LFM2.5-2.6B using mlx-vlm version 0.6.10. Refer to the original model...
mistralai/Ministral-3-3B-Reasoning-2512 converted to the LiteRT-LM (.litertlm) format for on-device inference with Google’s LiteRT-LM runtime (the engine behind the...