How to use Yova/SmallCap7M 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="Yova/SmallCap7M")
# Load model directly from transformers import SmallCap model = SmallCap.from_pretrained("Yova/SmallCap7M", device_map="auto")
https://huggingface.co/Yova/SmallCap7M/resolve/main/ln_ade20k_index_captions.json
hf download hf://Yova/SmallCap7M/ln_ade20k_index_captions.json
curl -L -o ln_ade20k_index_captions.json https://huggingface.co/Yova/SmallCap7M/resolve/main/ln_ade20k_index_captions.json
