tslim1's picture
Upload README.md with huggingface_hub
b89a53f verified
metadata
license: mit
license_link: >-
  https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
language:
  - multilingual
pipeline_tag: text-generation
tags:
  - nlp
  - code
  - mlx
  - mlx-my-repo
inference:
  parameters:
    temperature: 0.7
widget:
  - messages:
      - role: user
        content: Can you provide ways to eat combinations of bananas and dragonfruits?
base_model: microsoft/Phi-3-medium-128k-instruct

tslim1/Phi-3-medium-128k-instruct-mlx-8Bit

The Model tslim1/Phi-3-medium-128k-instruct-mlx-8Bit was converted to MLX format from microsoft/Phi-3-medium-128k-instruct using mlx-lm version 0.26.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("tslim1/Phi-3-medium-128k-instruct-mlx-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)