You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have trained and fine-tuned the ChatUniVi v1.5 model. For training, I set the parameter --model_name_or_path to /data/gs/weights/vicuna-7b-v1.5 and used my custom datasets specified with --dataset as "New" or "FINETUNE."
During training, I set the --output_dir to outputs/, where I obtained the mm_projection.bin file along with other .bin and .model files.
My question is: For the evaluation script, what should I set as the $model_path? Should it point to vicuna-7b-v1.5, or should it refer to the files in the outputs/ directory?
The text was updated successfully, but these errors were encountered:
I have trained and fine-tuned the ChatUniVi v1.5 model. For training, I set the parameter
--model_name_or_path
to/data/gs/weights/vicuna-7b-v1.5
and used my custom datasets specified with--dataset
as "New" or "FINETUNE."Now, I am trying to run the evaluation script as described in the [Chat-UniVi documentation](https://github.com/PKU-YuanGroup/Chat-UniVi/blob/main/TRAIN_AND_VALIDATE.md#step-1-load-the-model-to-generate-results-1).
During training, I set the
--output_dir
tooutputs/
, where I obtained themm_projection.bin
file along with other.bin
and.model
files.My question is: For the evaluation script, what should I set as the
$model_path
? Should it point tovicuna-7b-v1.5
, or should it refer to the files in theoutputs/
directory?The text was updated successfully, but these errors were encountered: