Weiyao-Li

Please try to reduce batch size or torch.cuda.empty_cache() to adjust. You can also use nvidia-smi to oversee what's going on and adjust the model based on your GPU. I ran...

Seems similar to a null pointer exception problem because the object itself does not exist. You should start from this and look for this "empty" object. It is possible that...

https://github.com/AI4Finance-Foundation/FinGPT-Research

!pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate

You need to restart the session if this happened. You may also refer to this repo for more detailed explanation with my articles inside. https://github.com/AI4Finance-Foundation/FinGPT-Research

I am not too sure about the extraction of financial info part. But you may use the script in my repo here for running fingpt. https://github.com/AI4Finance-Foundation/FinGPT-Research

Could you try google colab with A100 or TPU. Did you make any progress or still having any issue now?

add !pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate at the beginning of the code