Hugging Face's logo

lightonai
/
LightOnOCR-2-1B

Image-Text-to-Text
Transformers
Safetensors
mistral3
text-generation
ocr
document-understanding
vision-language
pdf
tables
forms
conversational
Eval Results
🇪🇺 Region: EU
Model card Files
xet
 Community
38

Fix typo in model architecture class name

#12
by Xenova HF Staff - opened
base: refs/heads/main
←
from: refs/pr/12
Discussion Files changed
+1
-1
Fix typo on model architecture name288c8a80
Xenova

See https://github.com/huggingface/transformers/blob/10e97cd508218546ef681a2c9b4c519ac0d927c3/src/transformers/models/lighton_ocr/modeling_lighton_ocr.py#L314

Xenova changed pull request title from Fix typo on model architecture name to Fix typo in model architecture class name
staghado
 LightOn AI org

Hi,
Thanks for the PR!
We actually need architectures to be a list of size 2:

"architectures": [
    "LightOnOcrForConditionalGeneration",
    "LightOnOCRForConditionalGeneration"
  ]

as vllm implementation uses capital letter OCR
Xenova

Hmm I see! Maybe @Molbap can help out here :)

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment