How to use anmol-unitmole/image-caption-generation-vision-encoder-decoder-model with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="anmol-unitmole/image-caption-generation-vision-encoder-decoder-model")
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("anmol-unitmole/image-caption-generation-vision-encoder-decoder-model") model = AutoModelForMultimodalLM.from_pretrained("anmol-unitmole/image-caption-generation-vision-encoder-decoder-model", device_map="auto")
How to use anmol-unitmole/image-caption-generation-vision-encoder-decoder-model with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-to-text', 'anmol-unitmole/image-caption-generation-vision-encoder-decoder-model');
