license: apache-2.0 base_model: junafinity/Ornith-1.5-9B-uncensored library_name: transformers pipeline_tag: image-text-to-text tags:

• ornith
• qwen3_5
• abliterated
• uncensored
• zerofuse
• multimodal
• vision
• mlx
• mlx-my-repo

keXjos/Ornith-1.5-9B-uncensored-mlx-5Bit

The Model keXjos/Ornith-1.5-9B-uncensored-mlx-5Bit was converted to MLX format from junafinity/Ornith-1.5-9B-uncensored using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("keXjos/Ornith-1.5-9B-uncensored-mlx-5Bit")

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)