KYUNGYONG/DNA-R1-4bit

The Model KYUNGYONG/DNA-R1-4bit was converted to MLX format from dnotitia/DNA-R1 using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/DNA-R1-4bit")

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)
Downloads last month
6
Safetensors
Model size
2.29B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for KYUNGYONG/DNA-R1-4bit

Base model

microsoft/phi-4
Finetuned
dnotitia/DNA-R1
Quantized
(7)
this model