metadata
license: cc-by-4.0
base_model: nvidia/OpenMath-Nemotron-32B
datasets:
- nvidia/OpenMathReasoning
language:
- en
tags:
- nvidia
- math
- mlx
library_name: mlx
pipeline_tag: text-generation
abalogh/OpenMath-Nemotron-32B-4bit
This model abalogh/OpenMath-Nemotron-32B-4bit was converted to MLX format from nvidia/OpenMath-Nemotron-32B using mlx-lm version 0.23.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("abalogh/OpenMath-Nemotron-32B-4bit")
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)