llms

Generate Text with LLMs and MLX

The easiest way to get started is to install the mlx-lm package:

With pip:

pip install mlx-lm

With conda:

conda install -c conda-forge mlx-lm

The mlx-lm package also has:

• LoRA and QLoRA fine-tuning
• Merging models
• HTTP model serving

Python API

You can use mlx-lm as a module:

from mlx_lm import load, generate

model, tokenizer = load("mistralai/Mistral-7B-Instruct-v0.1")

response = generate(model, tokenizer, prompt="hello", verbose=True)

To see a description of all the arguments you can do:

>>> help(generate)

The mlx-lm package also comes with functionality to quantize and optionally upload models to the Hugging Face Hub.

You can convert models in the Python API with:

from mlx_lm import convert

upload_repo = "mlx-community/My-Mistral-7B-v0.1-4bit"

convert("mistralai/Mistral-7B-v0.1", quantize=True, upload_repo=upload_repo)

This will generate a 4-bit quantized Mistral-7B and upload it to the repo mlx-community/My-Mistral-7B-v0.1-4bit. It will also save the converted model in the path mlx_model by default.

To see a description of all the arguments you can do:

>>> help(convert)

Command Line

You can also use mlx-lm from the command line with:

mlx_lm.generate --model mistralai/Mistral-7B-Instruct-v0.1 --prompt "hello"

This will download a Mistral 7B model from the Hugging Face Hub and generate text using the given prompt.

For a full list of options run:

mlx_lm.generate --help

To quantize a model from the command line run:

mlx_lm.convert --hf-path mistralai/Mistral-7B-Instruct-v0.1 -q

For more options run:

mlx_lm.convert --help

You can upload new models to Hugging Face by specifying --upload-repo to convert. For example, to upload a quantized Mistral-7B model to the MLX Hugging Face community you can do:

mlx_lm.convert \
    --hf-path mistralai/Mistral-7B-v0.1 \
    -q \
    --upload-repo mlx-community/my-4bit-mistral

Supported Models

The example supports Hugging Face format Mistral, Llama, and Phi-2 style models. If the model you want to run is not supported, file an issue or better yet, submit a pull request.

Here are a few examples of Hugging Face models that work with this example:

• mistralai/Mistral-7B-v0.1
• meta-llama/Llama-2-7b-hf
• deepseek-ai/deepseek-coder-6.7b-instruct
• 01-ai/Yi-6B-Chat
• microsoft/phi-2
• mistralai/Mixtral-8x7B-Instruct-v0.1
• Qwen/Qwen-7B
• pfnet/plamo-13b
• pfnet/plamo-13b-instruct
• stabilityai/stablelm-2-zephyr-1_6b

Most Mistral, Llama, Phi-2, and Mixtral style models should work out of the box.

For some models (such as Qwen and plamo) the tokenizer requires you to enable the trust_remote_code option. You can do this by passing --trust-remote-code in the command line. If you don't specify the flag explicitly, you will be prompted to trust remote code in the terminal when running the model.

For Qwen models you must also specify the eos_token. You can do this by passing --eos-token "<|endoftext|>" in the command line.

These options can also be set in the Python API. For example:

model, tokenizer = load(
    "qwen/Qwen-7B",
    tokenizer_config={"eos_token": "<|endoftext|>", "trust_remote_code": True},
)