README.md

metadata

license: mit
license_link: https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE
language:
  - en
base_model: microsoft/Phi-4-reasoning-plus
pipeline_tag: text-generation
tags:
  - phi
  - nlp
  - math
  - code
  - chat
  - conversational
  - reasoning
  - mlx
inference:
  parameters:
    temperature: 0
widget:
  - messages:
      - role: user
        content: What is the derivative of x^2?
library_name: mlx

Phi-4-reasoning-Plus-6bit

This model Phi-4-reasoning-Plus-6bit was converted to MLX format from microsoft/Phi-4-reasoning-plus using mlx-lm version 0.24.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Phi-4-reasoning-Plus-6bit")

prompt = "hello"

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

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