Image-to-Text
PEFT
Safetensors
Portuguese
English
vision-language
table-extraction
scientific-figures
markdown-table
lightonocr
qwen2.5-vl
qwen3-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
docs(eval): add 7B evaluation metrics inside subfolder
Browse files
qwen2_5_vl_7b/eval_report_7b.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"valid_table": 0.9973190348525469,
|
| 3 |
+
"exact_match": 0.002680965147453083,
|
| 4 |
+
"edit_similarity": 0.38106812583065297,
|
| 5 |
+
"rouge_l": 0.384215920331165,
|
| 6 |
+
"rouge_1": 0.4313245229429092,
|
| 7 |
+
"rouge_2": 0.23438600558595007,
|
| 8 |
+
"bleu_4": 0.19265916634631913,
|
| 9 |
+
"cell_precision": 0.47449411624740195,
|
| 10 |
+
"cell_recall": 0.6043179468792442,
|
| 11 |
+
"cell_f1": 0.43105424843380974,
|
| 12 |
+
"cell_rmse": 1.2001784360768568,
|
| 13 |
+
"cell_rne": 0.004605617228839706,
|
| 14 |
+
"teds": 0.43956215186081643,
|
| 15 |
+
"icdar_rms": 0.602554720605129,
|
| 16 |
+
"icdar_score": 0.5210584362329728
|
| 17 |
+
}
|