Text Generation
MLX
Safetensors
qwen2
chat
conversational
Eval Results
8-bit precision
Edit model card

mlx-community/magnum-v2-72b

The Model mlx-community/magnum-v2-72b was converted to MLX format from anthracite-org/magnum-v2-72b using mlx-lm version 0.19.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/magnum-v2-72b")

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
10
Safetensors
Model size
20.5B params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.

Model tree for mlx-community/magnum-v2-72b

Base model

Qwen/Qwen2-72B
Quantized
(5)
this model

Datasets used to train mlx-community/magnum-v2-72b

Evaluation results