Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

IDEA-CCNL
/
Taiyi-BLIP-750M-Chinese

Image-to-Text
Transformers
PyTorch
Safetensors
Chinese
blip
image-text-to-text
Model card Files Files and versions
xet
Community
4

Instructions to use IDEA-CCNL/Taiyi-BLIP-750M-Chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use IDEA-CCNL/Taiyi-BLIP-750M-Chinese 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="IDEA-CCNL/Taiyi-BLIP-750M-Chinese")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("IDEA-CCNL/Taiyi-BLIP-750M-Chinese")
    model = AutoModelForMultimodalLM.from_pretrained("IDEA-CCNL/Taiyi-BLIP-750M-Chinese", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
Taiyi-BLIP-750M-Chinese
6.01 GB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 9 commits
wuxiaojun's picture
wuxiaojun
update: tags
88937d6 about 3 years ago
  • .gitattributes
    1.53 kB
    FIRST: add model over 3 years ago
  • README.md
    111 Bytes
    update: tags about 3 years ago
  • added_tokens.json
    39 Bytes
    FIRST: add model over 3 years ago
  • config.json
    4.7 kB
    FIRST: add model over 3 years ago
  • model.safetensors
    3.01 GB
    xet
    Adding `safetensors` variant of this model (#2) about 3 years ago
  • preprocessor_config.json
    445 Bytes
    FIRST: add model over 3 years ago
  • pytorch_model.bin
    3.01 GB
    xet
    FEAT: update weight over 3 years ago
  • special_tokens_map.json
    244 Bytes
    FIRST: add model over 3 years ago
  • tokenizer_config.json
    490 Bytes
    FIRST: add model over 3 years ago
  • vocab.txt
    110 kB
    FIRST: add model over 3 years ago