Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ pipeline_tag: visual-question-answering
|
|
12 |
|
13 |
## Model Description
|
14 |
|
15 |
-
**paligemma-3b-tablevqa-896-lora** is a fine-tuned version of the **[google/paligemma-3b-ft-docvqa-896](https://huggingface.co/google/paligemma-3b-ft-docvqa-896)** model,
|
16 |
trained specifically on the **[table-vqa](https://huggingface.co/datasets/cmarkea/table-vqa)** dataset published by Crédit Mutuel Arkéa. This model leverages the
|
17 |
**LoRA** (Low-Rank Adaptation) technique, which significantly reduces the computational complexity of fine-tuning while maintaining high performance. The model operates
|
18 |
in bfloat16 precision for efficiency, making it an ideal solution for resource-constrained environments.
|
@@ -47,7 +47,7 @@ import requests
|
|
47 |
import torch
|
48 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
49 |
|
50 |
-
model_id = "cmarkea/paligemma-tablevqa-896-lora"
|
51 |
|
52 |
# Sample image for inference
|
53 |
url = "https://datasets-server.huggingface.co/cached-assets/cmarkea/table-vqa/--/c26968da3346f92ab6bfc5fec85592f8250e23f5/--/default/train/22/image/image.jpg?Expires=1728915081&Signature=Zkrd9ZWt5b9XtY0UFrgfrTuqo58DHWIJ00ZwXAymmL-mrwqnWWmiwUPelYOOjPZZdlP7gAvt96M1PKeg9a2TFm7hDrnnRAEO~W89li~AKU2apA81M6AZgwMCxc2A0xBe6rnCPQumiCGD7IsFnFVwcxkgMQXyNEL7bEem6cT0Cief9DkURUDCC-kheQY1hhkiqLLUt3ITs6o2KwPdW97EAQ0~VBK1cERgABKXnzPfAImnvjw7L-5ZXCcMJLrvuxwgOQ~DYPs456ZVxQLbTxuDwlxvNbpSKoqoAQv0CskuQwTFCq2b5MOkCCp9zoqYJxhUhJ-aI3lhyIAjmnsL4bhe6A__&Key-Pair-Id=K3EI6M078Z3AC3"
|
|
|
12 |
|
13 |
## Model Description
|
14 |
|
15 |
+
**paligemma-3b-ft-tablevqa-896-lora** is a fine-tuned version of the **[google/paligemma-3b-ft-docvqa-896](https://huggingface.co/google/paligemma-3b-ft-docvqa-896)** model,
|
16 |
trained specifically on the **[table-vqa](https://huggingface.co/datasets/cmarkea/table-vqa)** dataset published by Crédit Mutuel Arkéa. This model leverages the
|
17 |
**LoRA** (Low-Rank Adaptation) technique, which significantly reduces the computational complexity of fine-tuning while maintaining high performance. The model operates
|
18 |
in bfloat16 precision for efficiency, making it an ideal solution for resource-constrained environments.
|
|
|
47 |
import torch
|
48 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
49 |
|
50 |
+
model_id = "cmarkea/paligemma-3b-ft-tablevqa-896-lora"
|
51 |
|
52 |
# Sample image for inference
|
53 |
url = "https://datasets-server.huggingface.co/cached-assets/cmarkea/table-vqa/--/c26968da3346f92ab6bfc5fec85592f8250e23f5/--/default/train/22/image/image.jpg?Expires=1728915081&Signature=Zkrd9ZWt5b9XtY0UFrgfrTuqo58DHWIJ00ZwXAymmL-mrwqnWWmiwUPelYOOjPZZdlP7gAvt96M1PKeg9a2TFm7hDrnnRAEO~W89li~AKU2apA81M6AZgwMCxc2A0xBe6rnCPQumiCGD7IsFnFVwcxkgMQXyNEL7bEem6cT0Cief9DkURUDCC-kheQY1hhkiqLLUt3ITs6o2KwPdW97EAQ0~VBK1cERgABKXnzPfAImnvjw7L-5ZXCcMJLrvuxwgOQ~DYPs456ZVxQLbTxuDwlxvNbpSKoqoAQv0CskuQwTFCq2b5MOkCCp9zoqYJxhUhJ-aI3lhyIAjmnsL4bhe6A__&Key-Pair-Id=K3EI6M078Z3AC3"
|