base_model: FiditeNemini/Qwen2.5-14B-DeepSeek-R1-1M-Uncensored
library_name: transformers
tags:

• mergekit
• merge
• mlx
• mlx-my-repo

cnfusion/Qwen2.5-14B-DeepSeek-R1-1M-Uncensored-mlx-4Bit

The Model cnfusion/Qwen2.5-14B-DeepSeek-R1-1M-Uncensored-mlx-4Bit was converted to MLX format from FiditeNemini/Qwen2.5-14B-DeepSeek-R1-1M-Uncensored using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cnfusion/Qwen2.5-14B-DeepSeek-R1-1M-Uncensored-mlx-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)