|
--- |
|
license: gemma |
|
datasets: |
|
- BUAADreamer/llava-en-zh-2k |
|
language: |
|
- en |
|
- zh |
|
library_name: transformers |
|
pipeline_tag: image-text-to-text |
|
base_model: google/paligemma-3b-mix-448 |
|
inference: false |
|
tags: |
|
- paligemma |
|
- llama-factory |
|
- mllm |
|
- vlm |
|
--- |
|
|
|
# PaliGemma-3B-Chat-v0.1 |
|
|
|
This model is fine-tuned from [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) using [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory). |
|
|
|
 |
|
|
|
## Usage |
|
|
|
```python |
|
import requests |
|
import torch |
|
from PIL import Image |
|
from transformers import AutoModelForVision2Seq, AutoProcessor, AutoTokenizer, TextStreamer |
|
|
|
|
|
model_id = "hiyouga/PaliGemma-3B-Chat-v0.1" |
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
processor = AutoProcessor.from_pretrained(model_id) |
|
model = AutoModelForVision2Seq.from_pretrained(model_id, torch_dtype="auto", device_map="auto") |
|
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) |
|
|
|
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true" |
|
image = Image.open(requests.get(url, stream=True).raw) |
|
pixel_values = processor(images=[image], return_tensors="pt").to(model.device)["pixel_values"] |
|
|
|
messages = [ |
|
{"role": "user", "content": "What is in this image?"} |
|
] |
|
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt") |
|
image_token_id = tokenizer.convert_tokens_to_ids("<image>") |
|
image_prefix = torch.empty((1, getattr(processor, "image_seq_length")), dtype=input_ids.dtype).fill_(image_token_id) |
|
input_ids = torch.cat((image_prefix, input_ids), dim=-1).to(model.device) |
|
|
|
generate_ids = model.generate(input_ids, pixel_values=pixel_values, streamer=streamer, max_new_tokens=50) |
|
``` |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.00001 |
|
- num_train_epochs: 3.0 |
|
- train_batch_size: 1 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 16 |
|
- seed: 42 |
|
- lr_scheduler_type: cosine |
|
- mixed_precision_training: bf16 |
|
|
|
### Framework versions |
|
|
|
- Pytorch 2.3.0 |
|
- Transformers 4.41.0 |
|
|
