metadata

license: mit
library_name: mlx
language:
  - en
base_model: Zyphra/ZR1-1.5B
datasets:
  - AI-MO/NuminaMath-CoT
  - codeparrot/apps
  - deepmind/code_contests
  - BAAI/TACO
  - MatrixStudio/Codeforces-Python-Submissions
pipeline_tag: text-generation
tags:
  - mlx

dinerburger/ZR1-1.5B-mlx-8bit

This model dinerburger/ZR1-1.5B-mlx-8bit was converted to MLX format from Zyphra/ZR1-1.5B using mlx-lm version 0.22.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("dinerburger/ZR1-1.5B-mlx-8bit")

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)