LFM2.5-1.2B-Instruct-4bit
This model mlx-community/LFM2.5-1.2B-Instruct-4bit was converted to MLX format from LiquidAI/LFM2.5-1.2B-Instruct using mlx-lm version 0.30.2. Модальности:Генерация текста Области применения:Диалог...
This model mlx-community/LFM2.5-1.2B-Instruct-4bit was converted to MLX format from LiquidAI/LFM2.5-1.2B-Instruct using mlx-lm version 0.30.2. Модальности:Генерация текста Области применения:Диалог...
> [!NOTE] > Includes Unsloth chat template fixes! For llama.cpp, use —jinja > Unsloth Dynamic 2.0 achieves superior...
LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and...
Эта модель mlx-community/LFM2-8B-A1B-8bit была преобразована в формат MLX из LiquidAI/LFM2-8B-A1B с использованием mlx-lm версии 0.28.2. Модальности:Генерация текста Области...
This is quantized version of LiquidAI/LFM2-1.2B-RAG created using llama.cpp Based on LFM2-1.2B, LFM2-1.2B-RAG is specialized in answering questions...
A lightweight model to do machine translation from Ukrainian to English based on recently published LFM2 model. Use...
This model mlx-community/LFM2-1.2B-6bit was converted to MLX format from LiquidAI/LFM2-1.2B using mlx-lm version 0.26.0. Модальности:Генерация текста Области применения:Диалог...
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,...
An 8.9M-parameter question-answering model that runs entirely offline on an ESP32-S3 microcontroller, answering espresso questions a piece at...
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,...