update transformers usage

README.md

@@ -169,49 +169,39 @@ Currently, the PaddleOCR-VL-1.5-0.9B model facilitates seamless inference via th
 ```python
 from PIL import Image
 import torch
-from transformers import AutoModelForCausalLM, AutoProcessor
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
 # ---- Settings ----
-model_path = "PaddlePaddle/PaddleOCR-VL"
+model_path = "PaddlePaddle/PaddleOCR-VL-1.5"
 image_path = "test.png"
-task = "ocr" # Options: 'ocr' | 'table' | 'chart' | 'formula'
+task = "ocr" # Options: 'ocr' | 'table' | 'chart' | 'formula' | 'spotting'
 # ------------------
 
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-
-PROMPTS = {
-    "ocr": "OCR:",
-    "table": "Table Recognition:",
-    "formula": "Formula Recognition:",
-    "chart": "Chart Recognition:",
-}
-
+model = AutoModelForImageTextToText.from_pretrained(model_path, dtype="bfloat16").to(DEVICE).eval()
+processor = AutoProcessor.from_pretrained(model_path)
 image = Image.open(image_path).convert("RGB")
-
-model = AutoModelForCausalLM.from_pretrained(
-    model_path, trust_remote_code=True, torch_dtype=torch.bfloat16
-).to(DEVICE).eval()
-processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
-
 messages = [
-    {"role": "user",         
-     "content": [
+    {
+        "role": "user",
+        "content": [
             {"type": "image", "image": image},
             {"type": "text", "text": PROMPTS[task]},
         ]
     }
 ]
 inputs = processor.apply_chat_template(
-    messages, 
-    tokenize=True, 
-    add_generation_prompt=True, 	
-    return_dict=True,
-    return_tensors="pt"
-).to(DEVICE)
-
-outputs = model.generate(**inputs, max_new_tokens=1024)
-outputs = processor.batch_decode(outputs, skip_special_tokens=True)[0]
-print(outputs)
+	messages,
+	add_generation_prompt=True,
+	tokenize=True,
+	return_dict=True,
+	return_tensors="pt",
+).to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=100)
+result = processor.decode(outputs[0][inputs["input_ids"].shape[-1]:-1])
+print(result)
 ```
 
 <details>
@@ -223,60 +213,41 @@ pip install flash-attn --no-build-isolation
 ```
 
 ```python
-import torch
-from transformers import AutoModelForCausalLM, AutoProcessor
 from PIL import Image
+import torch
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
 # ---- Settings ----
-model_path = "PaddlePaddle/PaddleOCR-VL"
+model_path = "PaddlePaddle/PaddleOCR-VL-1.5"
 image_path = "test.png"
-task = "ocr" # ← change to "table" | "chart" | "formula"
+task = "ocr" # Options: 'ocr' | 'table' | 'chart' | 'formula' | 'spotting'
 # ------------------
 
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-
-model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    trust_remote_code=True,
-    torch_dtype=torch.bfloat16,
-    attn_implementation="flash_attention_2", 
-).to(dtype=torch.bfloat16, device=DEVICE).eval()
-processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
-
-PROMPTS = {
-    "ocr": "OCR:",
-    "table": "Table Recognition:",
-    "chart": "Chart Recognition:",
-    "formula": "Formula Recognition:",
-}
+model = AutoModelForImageTextToText.from_pretrained(model_path, dtype="bfloat16", attn_implementation="flash_attention_2").to(DEVICE).eval()
+processor = AutoProcessor.from_pretrained(model_path)
+image = Image.open(image_path).convert("RGB")
 messages = [
     {
-        "role": "user", 
+        "role": "user",
         "content": [
-            {"type": "image", "image": Image.open(image_path).convert("RGB")},
-            {"type": "text",  "text": PROMPTS[task]}
+            {"type": "image", "image": image},
+            {"type": "text", "text": PROMPTS[task]},
         ]
     }
 ]
-
 inputs = processor.apply_chat_template(
-    messages, 
-    tokenize=True, 
-    add_generation_prompt=True, 	
-    return_dict=True,
-    return_tensors="pt"
-).to(DEVICE)
-
-with torch.inference_mode():
-    out = model.generate(
-        **inputs,
-        max_new_tokens=1024,
-        do_sample=False,
-        use_cache=True
-    )
-
-outputs = processor.batch_decode(out, skip_special_tokens=True)[0]
-print(outputs)
+	messages,
+	add_generation_prompt=True,
+	tokenize=True,
+	return_dict=True,
+	return_tensors="pt",
+).to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=100)
+result = processor.decode(outputs[0][inputs["input_ids"].shape[-1]:-1])
+print(result)
 ```
 
 </details>