```CODE: 
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="0xSero/GLM-4.7-REAP-50-W4A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)
```

ERROR: 
Traceback (most recent call last):
  File "/tmp/0xSero_GLM-4.7-REAP-50-W4A16_0mqIr0K.py", line 26, in <module>
    pipe = pipeline("text-generation", model="0xSero/GLM-4.7-REAP-50-W4A16")
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 1027, in pipeline
    framework, model = infer_framework_load_model(
                       ~~~~~~~~~~~~~~~~~~~~~~~~~~^
        adapter_path if adapter_path is not None else model,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    ...<5 lines>...
        **model_kwargs,
        ^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/pipelines/base.py", line 293, in infer_framework_load_model
    model = model_class.from_pretrained(model, **kwargs)
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 604, in from_pretrained
    return model_class.from_pretrained(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4881, in from_pretrained
    hf_quantizer, config, dtype, device_map = get_hf_quantizer(
                                              ~~~~~~~~~~~~~~~~^
        config, quantization_config, dtype, from_tf, from_flax, device_map, weights_only, user_agent
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 311, in get_hf_quantizer
    hf_quantizer = AutoHfQuantizer.from_config(
        config.quantization_config,
        pre_quantized=pre_quantized,
    )
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 185, in from_config
    return target_cls(quantization_config, **kwargs)
  File "/tmp/.cache/uv/environments-v2/57fea2d03e820408/lib/python3.13/site-packages/transformers/quantizers/quantizer_gptq.py", line 49, in __init__
    raise ImportError("Loading a GPTQ quantized model requires optimum (`pip install optimum`)")
ImportError: Loading a GPTQ quantized model requires optimum (`pip install optimum`)