File size: 2,332 Bytes
914642d e2e1cb9 914642d e2e1cb9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- multimodal
- aria
---
<!-- <p align="center">
<br>Aria</br>
</p> -->
This is a fork of the [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) model. The primary modification is the replacement of [grouped GEMM](https://github.com/tgale96/grouped_gemm) with a sequential MLP. In this setup, each expert is a `torch.nn.Linear` layer executed sequentially. This change facilitates easier quantization using current open-source libraries, which are optimized to quantize `nn.Linear` layers.
## Quick Start
### Installation
```
pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
pip install flash-attn --no-build-isolation
```
### Inference
```python
import requests
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor
model_id_or_path = "rhymes-ai/Aria-sequential_mlp"
model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
image = Image.open(requests.get(image_path, stream=True).raw)
messages = [
{
"role": "user",
"content": [
{"text": None, "type": "image"},
{"text": "what is the image?", "type": "text"},
],
}
]
text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=text, images=image, return_tensors="pt")
inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
inputs = {k: v.to(model.device) for k, v in inputs.items()}
with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
output = model.generate(
**inputs,
max_new_tokens=500,
stop_strings=["<|im_end|>"],
tokenizer=processor.tokenizer,
do_sample=True,
temperature=0.9,
)
output_ids = output[0][inputs["input_ids"].shape[1]:]
result = processor.decode(output_ids, skip_special_tokens=True)
print(result)
``` |