Revert "update readme"

This reverts commit ad9ba0dc580ec9c0b76db76e799ea527caa21f55.

README.md

@@ -60,10 +60,7 @@ base_model:
 ## Quick Start
 ### Installation
 ```
-# Install transformers from GitHub until the next release includes the Aria model
-pip install git+https://github.com/huggingface/transformers.git
-
-pip install accelerate sentencepiece torchvision requests torch Pillow
+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
 
 # For better inference performance, you can install grouped-gemm, which may take 3-5 minutes to install
@@ -80,24 +77,23 @@ Here is a code snippet to show you how to use Aria.
 import requests
 import torch
 from PIL import Image
+from transformers import AutoModelForCausalLM, AutoProcessor
 
-from transformers import AriaProcessor, AriaForConditionalGeneration
+model_id_or_path = "rhymes-ai/Aria"
 
+model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
 
-model_id_or_path = "rhymes-ai/Aria"
-model = AriaForConditionalGeneration.from_pretrained(
-    model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16
-)
+processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
 
-processor = AriaProcessor.from_pretrained(model_id_or_path)
+image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
 
-image = Image.open(requests.get("http://images.cocodataset.org/val2017/000000039769.jpg", stream=True).raw)
+image = Image.open(requests.get(image_path, stream=True).raw)
 
 messages = [
     {
         "role": "user",
         "content": [
-            {"type": "image"},
+            {"text": None, "type": "image"},
             {"text": "what is the image?", "type": "text"},
         ],
     }
@@ -105,20 +101,22 @@ messages = [
 
 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(torch.bfloat16)
-inputs.to(model.device)
-
-output = model.generate(
-    **inputs,
-    max_new_tokens=15,
-    stop_strings=["<|im_end|>"],
-    tokenizer=processor.tokenizer,
-    do_sample=True,
-    temperature=0.9,
-)
-output_ids = output[0][inputs["input_ids"].shape[1]:]
-response = processor.decode(output_ids, skip_special_tokens=True)
-print(response)
+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)
 ```
 
 ### Advanced Inference and Fine-tuning