|
--- |
|
base_model: google/paligemma-3b-pt-224 |
|
library_name: peft |
|
license: gemma |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: finetuned_paligemma_vqav2_small |
|
results: [] |
|
--- |
|
|
|
# finetuned_paligemma_vqav2_small |
|
|
|
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) using the QLoRA |
|
technique on a small chunk of [vqav2 dataset](https://huggingface.co/datasets/merve/vqav2-small) by [Merve](https://huggingface.co/merve). |
|
|
|
## How to Use? |
|
|
|
```python |
|
import torch |
|
import requests |
|
|
|
from PIL import Image |
|
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration |
|
|
|
pretrained_model_id = "google/paligemma-3b-pt-224" |
|
finetuned_model_id = "pyimagesearch/finetuned_paligemma_vqav2_small" |
|
|
|
processor = AutoProcessor.from_pretrained(pretrained_model_id) |
|
finetuned_model = PaliGemmaForConditionalGeneration.from_pretrained(finetuned_model_id) |
|
|
|
prompt = "What is behind the cat?" |
|
image_file = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cat.png?download=true" |
|
raw_image = Image.open(requests.get(image_file, stream=True).raw) |
|
|
|
inputs = processor(raw_image.convert("RGB"), prompt, return_tensors="pt") |
|
output = finetuned_model.generate(**inputs, max_new_tokens=20) |
|
|
|
print(processor.decode(output[0], skip_special_tokens=True)[len(prompt):]) |
|
# gramophone |
|
``` |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
%3C%2Fspan%3E%3C%2Fspan%3E%3C!-- HTML_TAG_END --> |
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.0 |
|
- Transformers 4.46.0.dev0 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
