Update README.md

README.md

@@ -132,38 +132,40 @@ We tested **Next2 0.8B** against its base model and other models in the sub-2B c
 You can easily run **Next2 0.8B** on almost any machine with Python installed. Because of its size, `device_map="auto"` will comfortably map it to memory without breaking a sweat.
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
+from PIL import Image
 import torch
 
-model_id = "Lamapi/next2-0.8b"
+model_id = "thelamapi/next2-0.8b"
 
-# Load Tokenizer and Model
+model = AutoModelForCausalLM.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id) # For vision.
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, 
-    torch_dtype=torch.float16, 
-    device_map="auto"
-)
-
-# Chat Template Setup
-messages =[
-    {"role": "system", "content": "Sen Next2'sin, Lamapi tarafından Türkiye'de geliştirilmiş, mantıksal düşünebilen ve Türkçe'yi kusursuz kullanan bir yapay zeka asistanısın. Yanıtlarını düşünerek ve adım adım ver."},
-    {"role": "user", "content": "Kuantum bilgisayarların geleneksel bilgisayarlara göre avantajını basit bir mantıkla açıklar mısın?"}
+
+
+# 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"}
+    ]
+  }
 ]
 
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+# 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"]
 
-# Generate with Thinking Mode optimal parameters
-outputs = model.generate(
-    **inputs, 
-    max_new_tokens=512,
-    temperature=0.6,
-    top_p=0.95,
-    repetition_penalty=1.1
-)
 
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# 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))
 ```
 
 ---