J

Janus Pro 7B 4bit

Developed by wnma3mz
A 4-bit quantized version based on deepseek-ai/Janus-Pro-7B, optimized for Apple chip devices and suitable for chat tasks.
Downloads 99
Release Time : 1/30/2025

Model Overview

This model is an optimized version of deepseek-ai/Janus-Pro-7B, featuring 4-bit quantization, conversion to safetensors format, and added chat templates, making it ideal for macOS (Apple chip) devices.

Model Features

4-bit Quantization
The LLM portion is quantized to 4 bits, reducing model size and computational resource requirements.
safetensors Format
Model weights are updated from bin files to safetensors format, improving security and loading efficiency.
Chat Template Support
Added chat_template for easier deployment and use in chat tasks.
Apple Chip Optimization
Optimized for macOS (Apple chip) devices using the mlx framework for enhanced operational efficiency.

Model Capabilities

Text generation
Chat

Use Cases

Chat Applications
Smart Assistant
Deploy as an intelligent chat assistant to provide natural and smooth conversational experiences.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase