Bug: SyntaxError in generated atomgpt_compiled_module_mllama.py
What happens
Running the inverse vision script from the notebook, fails during dynamic codegen with a syntax error :
python atomgpt/inverse_models/inverse_vision_predict.py \
--image_path atomgpt/examples/inverse_model_vision/FeTe.png \
--formula FeTe
Error excerpt:
File "/tmp/atomgpt_compiled_cache/atomgpt_compiled_module_mllama.py", line 594
custom_intro="""
^^^^^^^^^^^^^^^^
SyntaxError: invalid syntax. Maybe you meant '==' or ':=' instead of '='?
...
RuntimeError: Direct module loading failed for atomgpt_compiled_module_mllama
Environment
- Python 3.11
- OS: Linux HPC node
relevant dependencies = [
"agapi>=2025.9.15",
"bitsandbytes>=0.47.0",
"colorama>=0.4.6",
"datasets>=4.1.1",
"defusedxml>=0.7.1",
"h5py>=3.14.0",
"jarvis-tools>=2025.5.30",
"jupyter>=1.1.1",
"lxml>=6.0.1",
"matplotlib>=3.10.6",
"numpy>=2.3.3",
"openai>=1.108.1",
"opencv-python>=4.11.0.86",
"pandas>=2.3.2",
"peft>=0.17.1",
"pillow>=11.3.0",
"torch>=2.8.0",
"transformers>=4.56.2",
"triton>=3.4.0",
"trl==0.15.2",
]
Bug: SyntaxError in generated
atomgpt_compiled_module_mllama.pyWhat happens
Running the inverse vision script from the notebook, fails during dynamic codegen with a syntax error :
Error excerpt:
Environment
relevant dependencies = [
"agapi>=2025.9.15",
"bitsandbytes>=0.47.0",
"colorama>=0.4.6",
"datasets>=4.1.1",
"defusedxml>=0.7.1",
"h5py>=3.14.0",
"jarvis-tools>=2025.5.30",
"jupyter>=1.1.1",
"lxml>=6.0.1",
"matplotlib>=3.10.6",
"numpy>=2.3.3",
"openai>=1.108.1",
"opencv-python>=4.11.0.86",
"pandas>=2.3.2",
"peft>=0.17.1",
"pillow>=11.3.0",
"torch>=2.8.0",
"transformers>=4.56.2",
"triton>=3.4.0",
"trl==0.15.2",
]