metadata
base_model: unsloth/Phi-4-mini-instruct
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE
language:
- multilingual
pipeline_tag: text-generation
tags:
- phi
- phi4
- unsloth
- nlp
- code
- microsoft
- math
- chat
- conversational
- mlx
- mlx-my-repo
library_name: transformers
mlxcommunity/Unsloth-Phi-4-mini-instruct-4Bit
The Model mlxcommunity/Unsloth-Phi-4-mini-instruct-4Bit was converted to MLX format from unsloth/Phi-4-mini-instruct using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("adrgrondin/Phi-4-mini-instruct-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)