phi-2-mlx-4Bit / README.md
jesusoctavioas's picture
Update README.md
6fef5f4 verified
metadata
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
language:
  - en
pipeline_tag: text-generation
tags:
  - nlp
  - code
  - mlx
base_model: microsoft/phi-2

jesusoctavioas/phi-2-mlx-4Bit

The Model jesusoctavioas/phi-2-mlx-4Bit was converted to MLX format from microsoft/phi-2 using mlx-lm version 0.28.3.

Use with mlx

# Create a virtual enviroment if needed.
python -m venv mlx-venv
# then activate the virtual enviroment if needed.
source mlx-venv/bin/activate
# then install mlx.
pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("jesusoctavioas/phi-2-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

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