Update README.md

README.md

@@ -37,27 +37,28 @@ pip install -U transformers accelerate
 Here is a simple example demonstrating how to load the model and perform code generation using the Hugging Face `pipeline` API:
 
 ```python
-import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
 model_id = "ByteDance-Seed/Seed-Coder-8B-Reasoning"
 
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model_id,
-    model_kwargs={"torch_dtype": torch.bfloat16},
-    device_map="auto",
-)
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
 
 messages = [
-    {"role": "user", "content": "Solve the following problem: Given an array of integers, find two numbers such that they add up to a specific target number."},
+    {"role": "user", "content": "Write a quick sort algorithm."},
 ]
 
-outputs = pipeline(
+input_ids = tokenizer.apply_chat_template(
     messages,
-    max_new_tokens=512,
-)
-print(outputs[0]["generated_text"][-1]["content"])
+    tokenize=True,
+    return_tensors="pt",
+    add_generation_prompt=True,  
+).to(model.device)
+
+outputs = model.generate(input_ids, max_new_tokens=32768)
+response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
+print(response)
 ```
 
 ## Evaluation