library_name: transformers
tags:

• Uncensored
• Abliterated
• Cubed Reasoning
• QwQ-32B
• reasoning
• thinking
• r1
• cot
• deepseek
• Qwen2.5
• Hermes
• DeepHermes
• DeepSeek
• DeepSeek-R1-Distill
• 128k context
• merge
• mlx
• mlx-my-repo
  base_model: DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored

bobig/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-4bit

The Model bobig/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-4bit was converted to MLX format from DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("bobig/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-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)