Video-Text-to-Text
Transformers
PyTorch
English
pixelrefer_qwen2
text-generation
multimodal large language model
large video-language model
Instructions to use Alibaba-DAMO-Academy/PixelRefer-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alibaba-DAMO-Academy/PixelRefer-2B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Alibaba-DAMO-Academy/PixelRefer-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Alibaba-DAMO-Academy/PixelRefer-2B: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/Alibaba-DAMO-Academy/PixelRefer-2B/resolve/main/tokenizer.json
- Command line
-
hf download hf://Alibaba-DAMO-Academy/PixelRefer-2B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Alibaba-DAMO-Academy/PixelRefer-2B/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 44f34ea4dfea3e3b8a1798f28cd0b151ed11e8967e8fdc580ac92434ad6a0246
- Size of remote file:
- 11.4 MB
- SHA256:
- 6f48dca4967a317c230cc71ae850c5584dcb277b5d2fc8983504595f3192c3b0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.