Image-Text-to-Text
PEFT
Safetensors
English
gemma4
lora
unsloth
vision-language
receipts
key-information-extraction
sroie
hacktoberfest
conversational
Instructions to use owaisnoe/gemma4-e2b-sroie-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use owaisnoe/gemma4-e2b-sroie-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E2B-it") model = PeftModel.from_pretrained(base_model, "owaisnoe/gemma4-e2b-sroie-lora") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download eval/error_categories.csv from owaisnoe/gemma4-e2b-sroie-lora: direct link, hf CLI and curl.
- Browser
- Download file 716 Bytes
-
https://huggingface.co/owaisnoe/gemma4-e2b-sroie-lora/resolve/main/eval/error_categories.csv
- Command line
-
hf download hf://owaisnoe/gemma4-e2b-sroie-lora/eval/error_categories.csv
-
curl -L -o error_categories.csv https://huggingface.co/owaisnoe/gemma4-e2b-sroie-lora/resolve/main/eval/error_categories.csv
716 Bytes
| ,fine-tuned,fine-tuned,fine-tuned,fine-tuned,prompted,prompted,prompted,prompted,plain,plain,plain,plain | |
| ,company,date,address,total,company,date,address,total,company,date,address,total | |
| "OCR-confusable chars (8/B, 0/O...)",0,0,3,0,0,0,2,0,0,0,4,0 | |
| correct,91,99,71,92,83,82,41,63,68,81,24,62 | |
| different amount,0,0,0,2,0,0,0,24,0,0,0,13 | |
| different date,0,1,0,0,0,2,0,0,0,0,0,0 | |
| different text,1,0,3,0,6,0,5,0,5,0,6,0 | |
| extra text,2,0,1,0,3,0,3,0,13,0,2,0 | |
| format only,1,0,1,3,2,16,22,10,8,18,28,9 | |
| near miss (sim >= 0.9),2,0,11,0,2,0,10,0,2,0,10,0 | |
| punctuation/spacing only,3,0,9,0,4,0,13,0,3,0,24,0 | |
| rounding (<= 0.05),0,0,0,3,0,0,0,3,0,0,0,3 | |
| truncated (part of gold),0,0,1,0,0,0,4,0,1,0,2,0 | |
| missing,0,0,0,0,0,0,0,0,0,1,0,13 | |