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
- Nemotron-Cascade
- reasoning
- general-purpose
- SFT
- RL
- pytorch
- mlx
- mlx-my-repo
base_model: nvidia/Nemotron-Cascade-8B-Thinking
introvoyz041/Nemotron-Cascade-8B-Thinking-mlx-4Bit
The Model introvoyz041/Nemotron-Cascade-8B-Thinking-mlx-4Bit was converted to MLX format from nvidia/Nemotron-Cascade-8B-Thinking using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/Nemotron-Cascade-8B-Thinking-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)