How to use harsh13333/gemma-clip-vqa_v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import GemmaCLIPVLM model = GemmaCLIPVLM.from_pretrained("harsh13333/gemma-clip-vqa_v1", device_map="auto")
https://huggingface.co/harsh13333/gemma-clip-vqa_v1/resolve/main/tokenizer_config.json
hf download hf://harsh13333/gemma-clip-vqa_v1/tokenizer_config.json
curl -L -o tokenizer_config.json https://huggingface.co/harsh13333/gemma-clip-vqa_v1/resolve/main/tokenizer_config.json
