Upload folder using huggingface_hub

README.md

@@ -20,6 +20,41 @@ pipe = pipeline(
     trust_remote_code=True, max_new_tokens=3,
 )
 print(pipe("Hello World!"))
+
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype="auto",
+    device_map="auto"
+)
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True  # Switches between thinking and non-thinking modes. Default is True.
+)
+print(text)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=128
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+print("thinking content:", thinking_content)
+print("content:", content)
 ```
 
 ### Codes to create this repo: