Visual Question Answering
Transformers
Safetensors
Vietnamese
openvivqa
scene-text-vqa
vietnamese
ocr
t5
Instructions to use Kus669/ViSceT5-ViTextVQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kus669/ViSceT5-ViTextVQA with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="Kus669/ViSceT5-ViTextVQA")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kus669/ViSceT5-ViTextVQA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
checkpoint-10990/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bffd56e75ce1475d78372cc4ddf4925ca9d41a712a2682149d89a99658072cad
|
| 3 |
size 14645
|
checkpoint-10990/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/content/ViSceT5/output/8e1f61b_ViTextVQA_qavit-gj-gr-consformer-gate-span-geo-wl-twoviews-p35-ocrboth0.05-ramp-bs16x1/checkpoint-
|
| 4 |
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 10990,
|
|
@@ -2360,6 +2360,22 @@
|
|
| 2360 |
"span_loss": 0.3171,
|
| 2361 |
"step": 10900,
|
| 2362 |
"view_loss": 0.5644
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2363 |
}
|
| 2364 |
],
|
| 2365 |
"logging_steps": 100,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4698611489502955,
|
| 3 |
+
"best_model_checkpoint": "/content/ViSceT5/output/8e1f61b_ViTextVQA_qavit-gj-gr-consformer-gate-span-geo-wl-twoviews-p35-ocrboth0.05-ramp-bs16x1/checkpoint-10990",
|
| 4 |
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 10990,
|
|
|
|
| 2360 |
"span_loss": 0.3171,
|
| 2361 |
"step": 10900,
|
| 2362 |
"view_loss": 0.5644
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 5.0,
|
| 2366 |
+
"eval_bleu1": 0.5827962320277351,
|
| 2367 |
+
"eval_bleu2": 0.532483076511092,
|
| 2368 |
+
"eval_bleu3": 0.4851027342384785,
|
| 2369 |
+
"eval_bleu4": 0.44686113334455274,
|
| 2370 |
+
"eval_cider": 3.385101343454942,
|
| 2371 |
+
"eval_em": 0.34510184287099904,
|
| 2372 |
+
"eval_em_f1": 0.4698611489502955,
|
| 2373 |
+
"eval_f1": 0.594620455029592,
|
| 2374 |
+
"eval_loss": 2.610790729522705,
|
| 2375 |
+
"eval_runtime": 576.8983,
|
| 2376 |
+
"eval_samples_per_second": 8.936,
|
| 2377 |
+
"eval_steps_per_second": 1.118,
|
| 2378 |
+
"step": 10990
|
| 2379 |
}
|
| 2380 |
],
|
| 2381 |
"logging_steps": 100,
|