You can deploy this model and start earning money today!

cnfusion/
DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlx

Name: DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlx
Availability: InStock

Views

No views yet

cnfusion/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlx

The Model cnfusion/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlx was converted to MLX format from alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("cnfusion/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlx")

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)