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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

sanjeevnv
/
multimodal-pretraining

Transformers
Safetensors
Model card Files Files and versions
xet
Community

Instructions to use sanjeevnv/multimodal-pretraining with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use sanjeevnv/multimodal-pretraining with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("sanjeevnv/multimodal-pretraining", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
multimodal-pretraining
17.9 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
sanjeevnv's picture
sanjeevnv
Document pretraining tokenizer behavior
7a5473c verified about 1 month ago
  • .gitattributes
    1.57 kB
    Add Nemotron-Nano tokenizer with generation markers for SFT loss masking 4 months ago
  • README.md
    2.49 kB
    Document pretraining tokenizer behavior about 1 month ago
  • chat_template.jinja
    482 Bytes
    Append </s> in pretraining chat template file about 1 month ago
  • config.json
    1.83 kB
    Remove BOS from tokenizer about 1 month ago
  • configuration_nemotron_h.py
    12.9 kB
    Add Nemotron-Nano tokenizer with generation markers for SFT loss masking 4 months ago
  • generation_config.json
    135 Bytes
    Use </s> as pretraining EOD token about 1 month ago
  • model.safetensors.index.json
    588 kB
    Add Nemotron-Nano tokenizer with generation markers for SFT loss masking 4 months ago
  • modeling_nemotron_h.py
    83.2 kB
    Add Nemotron-Nano tokenizer with generation markers for SFT loss masking 4 months ago
  • special_tokens_map.json
    278 Bytes
    Use </s> as pretraining EOD token about 1 month ago
  • tokenizer.json
    17.1 MB
    xet
    Remove BOS from tokenizer about 1 month ago
  • tokenizer_config.json
    178 kB
    Use </s> as pretraining EOD token about 1 month ago