Instructions to use m-i/UserLM-8b-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use m-i/UserLM-8b-mlx-fp16 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("m-i/UserLM-8b-mlx-fp16") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use m-i/UserLM-8b-mlx-fp16 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "m-i/UserLM-8b-mlx-fp16"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "m-i/UserLM-8b-mlx-fp16" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "m-i/UserLM-8b-mlx-fp16", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Download tokenizer.json from m-i/UserLM-8b-mlx-fp16: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/m-i/UserLM-8b-mlx-fp16/resolve/main/tokenizer.json
- Command line
-
hf download hf://m-i/UserLM-8b-mlx-fp16/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/m-i/UserLM-8b-mlx-fp16/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- ec2bedd01893e65563bdfd4e5e6756736c26147453d32d2b896b036fbdbefaba
- Size of remote file:
- 17.2 MB
- SHA256:
- 3f9a6668d8b9e32546100cbfea17354443a8d0c2af4693e74690b65389253159
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.