Update README.md

README.md

@@ -17,18 +17,42 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 
 ```python
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="oriental-lab/TinySwallow-1.5B-dolly", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+model_name = "oriental-lab/TinySwallow-1.5B-dolly"
 
-## Training procedure
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Do plants have life?"
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/twin1shun/huggingface/runs/wbfofu5p) 
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
+```
+
+## Training procedure
 
 This model was trained with SFT.