Update README.md

README.md

@@ -62,6 +62,33 @@ You can use this model just as any other HuggingFace models:
 from transformers import AutoModelForCausalLM, AutoTokenizer
 model = AutoModelForCausalLM.from_pretrained('fla-hub/rwkv7-0.4B-g1', trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-0.4B-g1', trust_remote_code=True)
+model = model.cuda() # Supported on Nvidia/AMD/Intel eg. model.xpu()
+prompt = "What is a large language model?"
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True  # Default is True, set to False to disable thinking
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024,
+    do_sample=True,
+    temperature=1.0,
+    top_p=0.3,
+    repetition_penalty=1.2
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=False)[0]
+print(response)
 ```
 
 ### Training Data