Update README.md

README.md

@@ -147,28 +147,28 @@ Designed for high-demand enterprise environments, **Next 32B** delivers superior
 **Note:** Due to the model size, we recommend using a GPU with at least 24GB VRAM (for 4-bit quantization) or 48GB+ (for 8-bit/FP16).
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+from unsloth import FastLanguageModel
 
-model_id = "Lamapi/next-32b"
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, 
-    torch_dtype=torch.float16, 
-    device_map="auto"
-)
+model, tokenizer = FastLanguageModel.from_pretrained("Lamapi/next-32b-4bit")
 
 messages = [
-    {"role": "system", "content": "You are Next-X1, an advanced reasoning AI assistant created by Lamapi. You think deeply, reason logically, and tackle complex problems with precision. Proudly made in Turkey."},
-    {"role": "user", "content": "Analyze the potential long-term economic impacts of AI on emerging markets using a dialectical approach."}
+    {"role": "system", "content": "You are Next-X1, an AI assistant created by Lamapi. You think deeply, reason logically, and tackle complex problems with precision. You are an helpful, smart, kind, concise AI assistant."},
+    {"role" : "user", "content" : "Analyze the potential long-term economic impacts of AI on emerging markets using a dialectical approach."}
 ]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize = False,
+    add_generation_prompt = True,
+    enable_thinking = True,
+)
 
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-
-outputs = model.generate(**inputs, max_new_tokens=512)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+from transformers import TextStreamer
+_ = model.generate(
+    **tokenizer(text, return_tensors = "pt").to("cuda"),
+    max_new_tokens = 1024, # Increase for longer outputs!
+    temperature = 0.7, top_p = 0.95, top_k = 400,
+    streamer = TextStreamer(tokenizer, skip_prompt = True),
+)
 ```
 
 ---