metadata

base_model: microsoft/phi-4
language:
  - en
library_name: transformers
license: mit
license_link: https://huggingface.co./microsoft/phi-4/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
  - phi
  - nlp
  - math
  - code
  - chat
  - conversational
  - mlx
inference:
  parameters:
    temperature: 0
widget:
  - messages:
      - role: user
        content: How should I explain the Internet?

mlx-community/phi-4-8bit

The Model mlx-community/phi-4-8bit was converted to MLX format from microsoft/phi-4 using mlx-lm version 0.20.6.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/phi-4-8bit")

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)