yizaochen
/

deepseek-ocr-3b-docvqa-lora

vision-language

Model card Files Files and versions

deepseek-ocr-3b-docvqa-lora

Commit History

Add modeling_deepseekv2.py with multi-image support

99a7cd2
verified

yizaochen commited on Jan 11

Add configuration_deepseek_v2.py with multi-image support

46632b0
verified

yizaochen commited on Jan 11

Add conversation.py with multi-image support

7ec04c4
verified

yizaochen commited on Jan 11

Add deepencoder.py with multi-image support

3900270
verified

yizaochen commited on Jan 11

Add updated modeling file with multi-image support in infer()

df95ec7
verified

yizaochen commited on Jan 11

Add updated modeling file with multi-image support in infer()

6166d96
verified

yizaochen commited on Jan 11

Add model card

87823c6
verified

yizaochen commited on Dec 28, 2025

Upload DeepSeek OCR LoRA model trained on DocVQA

6544926
verified

yizaochen commited on Dec 28, 2025

initial commit

021e286
verified

yizaochen commited on Dec 28, 2025