Macaw-LLM

Macaw-LLM copied to clipboard

Always have same response

5

Hi, I have loaded your pre-trained weights and tried some instructions. However, I found the model responded with the same answer no matter what image I gave. ```python model =...

kehanlu

Hi, when I run "preprocess_data_supervised.py" by using llama-7b-hf tokenizer, it shows "Using pad_token, but it is not set yet" and "Truncation was not explicitly activated but `max_length` is provided a...

wanghao-cst

Data filtering step

1

When processing the dataset, there is a filter criteria: if 'caption' in e['instruction'] or 'caption' in e['response'] or ' no ' in e['response'] or 'not' in e['response']: continue Why we...

chatsci

 how can i get those 2 json files?

Arbor334

Custom Dataset Finetuning

2

Could you add some pointers on how to use your trained model for fine-tuning on a custom dataset? Also which model weights need to be stored where for the inferencing...

saransh03sharma

If you install version 0.19.0 of accelerate listed in the current requirements.txt, you will encounter the following error. Therefore, I have updated the accelerate version to the latest one. ImportError:...

kacel33

Which tokenizer are you using? tokenizer = AutoTokenizer.from_pretrained('trained_models/llama_tokenizer') This seems to not work.

sbkim052

Can you share the numbers on the performance of the model? I am curious whether the audio signal improves the Video VQA at all

rohun-tripathi