mlx-Janus-Pro
Collection
8 items • Updated • 3
This model is derived from https://huggingface.co/deepseek-ai/Janus-Pro-1B and the main modifications are as follows
- bin files are updated to safetensors
- Add chat_template
4bit mainly refers to quantifying the LLM part to 4 bits.
Quick Start
In Macos (Apple silicon), use mlx framework https://github.com/wnma3mz/tLLM
tllm.server --model_path $MODEL_PATH
$MODEL_PATH like wnma3mz/Janus-Pro-1B-4bit
- Downloads last month
- 4
Model size
2B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for wnma3mz/Janus-Pro-1B
Base model
deepseek-ai/Janus-Pro-1B