Visual Question Answering
Transformers
Safetensors
Vietnamese
openvivqa
scene-text-vqa
vietnamese
ocr
t5
Instructions to use Kus669/ViSceT5-OpenViVQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kus669/ViSceT5-OpenViVQA 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-OpenViVQA")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kus669/ViSceT5-OpenViVQA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
checkpoint-9640/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 sha256:723aefe5358c7485c2ac21885353f7e3a6ecde96b5c2c02a8bcda7051030d90c
|
| 3 |
size 14645
|
checkpoint-9640/trainer_state.json
CHANGED
|
@@ -2087,6 +2087,22 @@
|
|
| 2087 |
"span_loss": 0.2957,
|
| 2088 |
"step": 9600,
|
| 2089 |
"view_loss": 0.5323
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2090 |
}
|
| 2091 |
],
|
| 2092 |
"logging_steps": 100,
|
|
|
|
| 2087 |
"span_loss": 0.2957,
|
| 2088 |
"step": 9600,
|
| 2089 |
"view_loss": 0.5323
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 5.0,
|
| 2093 |
+
"eval_bleu1": 0.5588900718658318,
|
| 2094 |
+
"eval_bleu2": 0.5005104980949288,
|
| 2095 |
+
"eval_bleu3": 0.4536136781109752,
|
| 2096 |
+
"eval_bleu4": 0.4160561728207932,
|
| 2097 |
+
"eval_cider": 3.748834295433214,
|
| 2098 |
+
"eval_em": 0.1382228490832158,
|
| 2099 |
+
"eval_em_f1": 0.36195135468742745,
|
| 2100 |
+
"eval_f1": 0.5856798602916391,
|
| 2101 |
+
"eval_loss": 2.5037269592285156,
|
| 2102 |
+
"eval_runtime": 437.6653,
|
| 2103 |
+
"eval_samples_per_second": 8.1,
|
| 2104 |
+
"eval_steps_per_second": 1.014,
|
| 2105 |
+
"step": 9640
|
| 2106 |
}
|
| 2107 |
],
|
| 2108 |
"logging_steps": 100,
|