language:

• en
• fr
• es
• pt
  tags:
• falcon3
• abliterated
• uncensored
• mlx
• mlx-my-repo
  base_model: huihui-ai/Falcon3-10B-Instruct-abliterated
  license: other
  license_name: falcon-llm-license
  license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
  library_name: transformers

mlx-community/Falcon3-10B-Instruct-abliterated-4bit

The Model mlx-community/Falcon3-10B-Instruct-abliterated-4bit was converted to MLX format from huihui-ai/Falcon3-10B-Instruct-abliterated using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Falcon3-10B-Instruct-abliterated-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)