metadata
license: cc-by-4.0
base_model: nvidia/OpenMath-Nemotron-14B-Kaggle
datasets:
- nvidia/OpenMathReasoning
language:
- en
tags:
- nvidia
- math
- mlx
- mlx-my-repo
library_name: transformers
introvoyz041/OpenMath-Nemotron-14B-Kaggle-mlx-4Bit
The Model introvoyz041/OpenMath-Nemotron-14B-Kaggle-mlx-4Bit was converted to MLX format from nvidia/OpenMath-Nemotron-14B-Kaggle using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/OpenMath-Nemotron-14B-Kaggle-mlx-4Bit")
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)