README.md

metadata

base_model: jondurbin/airoboros-33b-gpt4-1.4
datasets:
  - jondurbin/airoboros-gpt4-1.4
license: cc-by-nc-4.0
tags:
  - mlx

mlx-community/airoboros-33b-gpt4-1.4

The Model mlx-community/airoboros-33b-gpt4-1.4 was converted to MLX format from jondurbin/airoboros-33b-gpt4-1.4 using mlx-lm version 0.19.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/airoboros-33b-gpt4-1.4")

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)