Update README.md

README.md

@@ -224,59 +224,40 @@ Next 2.5's visual cortex allows it to rival or beat proprietary nano-models from
 Make sure you have the latest `transformers`, `torch`, `torchvision`, and `pillow` installed.
 
 ```python
-from transformers import AutoProcessor, AutoModelForCausalLM
-import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
 from PIL import Image
-import requests
-
-model_id = "Lamapi/next2.5-4b"
-
-# Load Model & Processor
-processor = AutoProcessor.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, 
-    torch_dtype=torch.float16, 
-    device_map="auto"
-)
-
-# Prepare Image
-url = "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/RealWorld/RealWorld-04.png"
-image = Image.open(requests.get(url, stream=True).raw)
-
-# Chat Template (With Thinking Mode enabled by default)
-messages =[
-    {
-        "role": "system", 
-        "content": "Sen Next 2.5'sin. Lamapi tarafından Türkiye'de geliştirilmiş, gelişmiş bir yapay zekasın. Yanıtlarını adım adım düşünerek ver."
-    },
-    {
-        "role": "user",
-        "content":[
-            {"type": "image", "image": image},
-            {"type": "text", "text": "Bu resimde tam olarak ne görüyorsun? Mantıksal çıkarımlar yaparak açıkla."}
-        ]
-    }
-]
+import torch
+
+model_id = "thelamapi/next2.5"
+
+model = AutoModelForCausalLM.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id) # For vision.
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-# Process Inputs
-text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)
-
-# Generate Output
-generated_ids = model.generate(
-    **inputs,
-    max_new_tokens=2048,
-    temperature=0.6,
-    top_p=0.95
-)
-
-# Decode
-generated_ids_trimmed =[
-    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+
+# Create a message in chat format
+messages = [
+  {"role": "system","content": [{"type": "text", "text": "You are Next2.5, a smart and concise AI assistant trained by Lamapi. Always respond in the user's language. Proudly made in Turkey."}]},
+
+  {
+      "role": "user","content": [
+      {"type": "text", "text": "Write a highly optimized Rust function to calculate the Fibonacci sequence using memoization"}
+    ]
+  }
 ]
-output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
 
-print(output_text)
+# Prepare input with Tokenizer
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)
+inputs = processor(text=prompt, return_tensors="pt")
+
+# Remove 'mm_token_type_ids' if it's not needed for text-only generation
+if "mm_token_type_ids" in inputs:
+    del inputs["mm_token_type_ids"]
+
+
+# Output from the model
+output = model.generate(**inputs, do_sample=True, temperature=0.7, max_new_tokens=128)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 ---