Adrian Gabriel

Is it possible to run labelImg on a remote linux GPU-Server?

2

We are using a remote linux GPU-Server for training and storing our data and are allowed to work with the data only on the server. We can operate on the...

Hi there, can I change the model that is being used for data generation? I would like to use the wizardLM model for instance.

Error loading fine-tuned wizard model

4

Hi guys, I have used your fine-tuning script on a custom data set to fine tune the wizardLm model. The training works without problems, the loss decreases and all the...

Hi guys, ther model and the tokenizer have to passed in as arguments into the evaluate() method within inference_wizardlm.py

Model used for generating training data?

1

Hi guys, what LLM are you using for generating the training data? It is the proprietary ChatGPT 3.5 Turbo right? Have you tried out open-source alternatives for data generation as...

Error while generating wizardlm weights: missing utils file in train_freeform.py

3

Hi guys, I followed the instructions to generate the weights from source. There is no file named "utils" imported in line 25 in train_freeform.py. Please provide that in the repo.

Hi team, great work first of all. I would like to use your framework for the domain of sports. I have a time series data of players in regards to...

Possible to use coordinates of pose estimation with pyomeca?

1

Hi folks, I am completely new to Biomechanics and have been looking at it only from the perspective of pose estimation. Is it possible to use the data of a...

How to write the prompt to tell the model that it should only generate the answers based on the context?

1

Hi guys, we have tried your model for a bigger number of documents (then used in the example code) and found that the model does not suse the provided documents...

Hey guys, I have two questions regarding the structure of your data set. In the ReadMe you say that you are using the "Alpaca" approach, where they use a triple...