mlx-Janus-Pro
Collection
8 items • Updated • 3
How to use from
MLX LMRun an OpenAI-compatible server
# Install MLX LM
uv tool install mlx-lm# Start the server
mlx_lm.server --model "wnma3mz/Janus-Pro-1B-LM-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "wnma3mz/Janus-Pro-1B-LM-4bit",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Quick Links
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 refers to quantifying the LLM part to 4 bits.
LM means that it contains only the language model part.
Quick Start
In Macos (Apple silicon), use mlx framework https://github.com/wnma3mz/tLLM
tllm.server --model_path $MODEL_PATH --hostname localhost --is_local --client_size 1
$MODEL_PATH like wnma3mz/Janus-Pro-1B-4bit
- Downloads last month
- 7
Model size
0.3B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for wnma3mz/Janus-Pro-1B-LM-4bit
Base model
deepseek-ai/Janus-Pro-1B
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm# Interactive chat REPL mlx_lm.chat --model "wnma3mz/Janus-Pro-1B-LM-4bit"