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

yizaochen
/
deepseek-ocr-3b-docvqa-lora

PEFT
Safetensors
lora
deepseek
ocr
docvqa
vision-language
Model card Files Files and versions
xet
Community

Instructions to use yizaochen/deepseek-ocr-3b-docvqa-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use yizaochen/deepseek-ocr-3b-docvqa-lora with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-OCR")
    model = PeftModel.from_pretrained(base_model, "yizaochen/deepseek-ocr-3b-docvqa-lora")
  • Notebooks
  • Google Colab
  • Kaggle
deepseek-ocr-3b-docvqa-lora
321 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
yizaochen's picture
yizaochen
Add modeling_deepseekv2.py with multi-image support
99a7cd2 verified 4 months ago
  • .gitattributes
    1.52 kB
    initial commit 5 months ago
  • README.md
    1.14 kB
    Add model card 5 months ago
  • adapter_config.json
    1.21 kB
    Upload DeepSeek OCR LoRA model trained on DocVQA 5 months ago
  • adapter_model.safetensors
    311 MB
    xet
    Upload DeepSeek OCR LoRA model trained on DocVQA 5 months ago
  • configuration_deepseek_v2.py
    10.6 kB
    Add configuration_deepseek_v2.py with multi-image support 4 months ago
  • conversation.py
    9.25 kB
    Add conversation.py with multi-image support 4 months ago
  • deepencoder.py
    38 kB
    Add deepencoder.py with multi-image support 4 months ago
  • modeling_deepseekocr.py
    42.1 kB
    Add updated modeling file with multi-image support in infer() 4 months ago
  • modeling_deepseekv2.py
    82.4 kB
    Add modeling_deepseekv2.py with multi-image support 4 months ago
  • special_tokens_map.json
    549 Bytes
    Upload DeepSeek OCR LoRA model trained on DocVQA 5 months ago
  • tokenizer.json
    9.98 MB
    Upload DeepSeek OCR LoRA model trained on DocVQA 5 months ago
  • tokenizer_config.json
    166 kB
    Upload DeepSeek OCR LoRA model trained on DocVQA 5 months ago