README.md

metadata

library_name: transformers
license: other
license_name: nvidia-open-model-license
license_link: >-
  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
pipeline_tag: text-generation
language:
  - en
tags:
  - nvidia
  - reasoning
  - math
  - code
  - reinforcement learning
  - pytorch
  - mlx
  - mlx-my-repo
base_model: nvidia/AceReason-Nemotron-14B

mlx-community/AceReason-Nemotron-14B-8bit

The Model mlx-community/AceReason-Nemotron-14B-8bit was converted to MLX format from nvidia/AceReason-Nemotron-14B using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/AceReason-Nemotron-14B-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)