Demetris Paschalides

> ```python > doc.user_data = {} > ``` Can you please provide a more complete example. I use your code snippet but unfortunately I have no access to the coref...

Hello, Sorry about that. The virtual environment is on `Python 3.10.12`. Also, what do you mean by "entire configuration"? I am running this on a server with 80 cores of...

Hello @alexsherstinsky, I am not passing a file. I followed the examples in the website, like in this [colab](https://colab.research.google.com/github/ludwig-ai/ludwig-docs/blob/master/docs/examples/llm/LLM_fine_tuning_for_Text_Classification_with_Ludwig_Python_API.ipynb), where the config is passed as a Python dictionary similar to...

Hello and thank you for your quick response. I saw this solution for a text-to-text fine-tuning. However, my goal is to leverage the potency of Llama2 for a unique case...

Thank you very much! I will try to run the text-to-text approach with the snippet provided. I don't have access to multiple GPUs, I am more interested to why fine-tuning...

Hey @alexsherstinsky. This is understandable, however, I am using the sharded version of abhishek/llama-2-7B-hf-small-shards. Shouldn't this work?

Thanks for your response @arnavgarg1. A flag would be nice yes. I will try with a lighter model as @alexsherstinsky said, just to see what happens.

@esh-b The issue is not that. I have the same problem, and after checking i got this error: `java.io.FileNotFoundException: \dev\stdin (The system cannot find the path specified)` But i cannot...