SiddhJagani's picture
Update README.md
ca16521 verified
metadata
base_model: TeichAI/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mlx
  - nvidia
  - cascade
  - lm-studio
license: apache-2.0
language:
  - en
datasets:
  - TeichAI/claude-4.5-opus-high-reasoning-250x

SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6

The Model SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6 was converted to MLX format from TeichAI/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6")

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)