license: gpl-3.0
language:

• en
• zh
  base_model: Orion-zhen/DeepSeek-R1-Distill-Llama-70B-abliterated
  tags:
• mlx

Fmuaddib/DeepSeek-R1-Distill-Llama-70B-abliterated-mlx-8Bit

The Model Fmuaddib/DeepSeek-R1-Distill-Llama-70B-abliterated-mlx-8Bit was converted to MLX format from Orion-zhen/DeepSeek-R1-Distill-Llama-70B-abliterated using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/DeepSeek-R1-Distill-Llama-70B-abliterated-mlx-8Bit")

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)