Antonio Scaiella
Antonio Scaiella
Msr vtt dataset have 10000 videos and 20 captions for each video but in this implementation only a video-caption pair for each example in train phase is considered. Therefore in...
Msr vtt dataset have 10000 videos and 20 captions for each video but in this implementation only a video-caption pair in train phase is considered. Therefore in total
I have the same question
@valentimarco Here are the corrections I made locally and now it works: in cheshire-cat/core/cat/factory/custom_embedder.py: ` def embed_documents(self, texts: List[str]) -> List[List[float]]: payload = json.dumps({"input": texts}) headers = {'Content-type': 'application/json', 'Accept':...
did you solve this ?
I have the same problem. I did finetuning without Lora of the openbmb/MiniCPM-V-2_6 model. After training for 5 epochs and testing the model I get: ` answer = model.chat( File...