Image-to-Text
PEFT
Safetensors
Portuguese
English
vision-language
table-extraction
scientific-figures
markdown-table
qwen2.5-vl
lora
icdar-metric-loss
Instructions to use lucasoc/sci-image-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lucasoc/sci-image-models with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct") model = PeftModel.from_pretrained(base_model, "lucasoc/sci-image-models") - Notebooks
- Google Colab
- Kaggle
Download eval_report_7b.json from lucasoc/sci-image-models: direct link, hf CLI and curl.
- Browser
- Download file 537 Bytes
-
https://huggingface.co/lucasoc/sci-image-models/resolve/main/eval_report_7b.json
- Command line
-
hf download hf://lucasoc/sci-image-models/eval_report_7b.json
-
curl -L -o eval_report_7b.json https://huggingface.co/lucasoc/sci-image-models/resolve/main/eval_report_7b.json
537 Bytes
| { | |
| "valid_table": 0.9973190348525469, | |
| "exact_match": 0.002680965147453083, | |
| "edit_similarity": 0.38106812583065297, | |
| "rouge_l": 0.384215920331165, | |
| "rouge_1": 0.4313245229429092, | |
| "rouge_2": 0.23438600558595007, | |
| "bleu_4": 0.19265916634631913, | |
| "cell_precision": 0.47449411624740195, | |
| "cell_recall": 0.6043179468792442, | |
| "cell_f1": 0.43105424843380974, | |
| "cell_rmse": 1.2001784360768568, | |
| "cell_rne": 0.004605617228839706, | |
| "teds": 0.43956215186081643, | |
| "icdar_rms": 0.602554720605129, | |
| "icdar_score": 0.5210584362329728 | |
| } |