Update README.md

README.md

@@ -70,53 +70,31 @@ Refer to [Sailor2 Website](https://sailorllm.github.io/) for more training detai
 ## Requirements
 The code of Sailor2 has been in the latest Hugging face transformers and we advise you to install `transformers==4.46.3`.
 
-## Quickstart
+### Quickstart
 
 Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.
 
 ```python
-import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-device = "cuda"
+device = "cuda" # the device to load the model
 
-model = AutoModelForCausalLM.from_pretrained(
-    'sail/Sailor2-20B-Chat',
-    torch_dtype=torch.bfloat16,
-    device_map="auto"
-)
-
-tokenizer = AutoTokenizer.from_pretrained('sail/Sailor2-1B-Chat')
-system_prompt= \
-'You are an AI assistant named Sailor2, created by Sea AI Lab. \
-As an AI assistant, you can answer questions in English, Chinese, and Southeast Asian languages \
-such as Burmese, Cebuano, Ilocano, Indonesian, Javanese, Khmer, Lao, Malay, Sundanese, Tagalog, Thai, Vietnamese, and Waray. \
-Your responses should be friendly, unbiased, informative, detailed, and faithful.'
-
-prompt = "Beri saya pengenalan singkat tentang model bahasa besar."
-# prompt = "Hãy cho tôi một giới thiệu ngắn gọn về mô hình ngôn ngữ lớn."
-# prompt = "ให้ฉันแนะนำสั้น ๆ เกี่ยวกับโมเดลภาษาขนาดใหญ่"
+model = AutoModelForCausalLM.from_pretrained("sail/Sailor2-1B", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("sail/Sailor2-1B")
 
-messages = [
-    {"role": "system", "content": system_prompt},
-    {"role": "user", "content": prompt}
-]
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
+input_message = "Model bahasa adalah model probabilistik" 
+### The given Indonesian input translates to 'A language model is a probabilistic model of.'
 
-model_inputs = tokenizer([text], return_tensors="pt").to(device)
-input_ids = model_inputs.input_ids.to(device)
+model_inputs = tokenizer([input_message], return_tensors="pt").to(device)
 
 generated_ids = model.generate(
-    input_ids,
-    max_new_tokens=512,
+    model_inputs.input_ids,
+    max_new_tokens=64
 )
 
 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=True)[0]
 print(response)
 ```