vimal00r comments

Repositories
Issues
Comments

Results 1 comments of


                                            vimal00r

💡 [REQUEST] - <title> How to Create the Multimodal embedding for text, image and videos using this model.

> 可以将padding换为left, 然后取outputs.last_hidden_state[:, -1, :] code = """ !pip install -q transformers bitsandbytes accelerate torch Pillow decord flash-attn --no-build-isolation from transformers import AutoTokenizer, AutoModel, AutoImageProcessor import torch from PIL import...