gpt2-xl-bf16

warshanks/gpt2-xl-bf16

The Model warshanks/gpt2-xl-bf16 was converted to MLX format from openai-community/gpt2-xl using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("warshanks/gpt2-xl-bf16")

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)