After deploying locally, I keep encountering errors when running the examples. Is there any solution

#1
by AndyLeaf666 - opened

(.venv_step3) D:\qr-code>d:/qr-code/.venv_step3/Scripts/python.exe d:/qr-code/test6.py
The tokenizer you are loading from 'D:\huggingface\Step3-VL-10B-AWQ' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the fix_mistral_regex=True flag when loading this tokenizer to fix this issue.
Encountered exception while importing configuration_step_vl: No module named 'configuration_step_vl'
Encountered exception while importing vision_encoder: No module named 'vision_encoder'
Traceback (most recent call last):
File "d:\qr-code\test6.py", line 24, in
model = AutoModelForCausalLM.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\qr-code.venv_step3\Lib\site-packages\transformers\models\auto\auto_factory.py", line 586, in from_pretrained
model_class = get_class_from_dynamic_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\qr-code.venv_step3\Lib\site-packages\transformers\dynamic_module_utils.py", line 604, in get_class_from_dynamic_module
final_module = get_cached_module_file(
^^^^^^^^^^^^^^^^^^^^^^^
File "d:\qr-code.venv_step3\Lib\site-packages\transformers\dynamic_module_utils.py", line 427, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\qr-code.venv_step3\Lib\site-packages\transformers\dynamic_module_utils.py", line 260, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: configuration_step_vl, vision_encoder. Run pip install configuration_step_vl vision_encoder

QuantTrio org

Based on the logs, I believe that the current version of Transformers does not yet support configuration_step_vl. In addition, all of our quantized models have only been tested on Linux systems using the vLLM inference engine. The Windows environment and the Transformers backend have not undergone comprehensive testing.

Sign up or log in to comment