Update README.md

README.md

@@ -28,6 +28,54 @@ __Ring-1T__ remains under continuous training. While the preview version already
     <img src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*Q1NZT4ti6aoAAAAAgBAAAAgAemJ7AQ/original"/>
 <p>
 
+
+## Quickstart
+
+### 🤗 Hugging Face Transformers
+
+Here is a code snippet to show you how to use the chat model with `transformers`:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "inclusionAI/Ring-1T-preview"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    dtype="auto",
+    device_map="auto",
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Give me a short introduction to large language models."
+messages = [
+    {"role": "system", "content": "You are Ling, an assistant created by inclusionAI"},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt", return_token_type_ids=False).to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=8192
+)
+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]
+```
+
+### 🤖 ModelScope
+
+If you're in mainland China, we strongly recommend you to use our model from 🤖 <a href="https://modelscope.cn/organization/inclusionAI">ModelScope</a>.
+
+
 ## License
 
 This code repository is licensed under [the MIT License](https://github.com/inclusionAI/Ling-V2/blob/master/LICENCE).