Update README.md

README.md

@@ -21,12 +21,31 @@ Aligner is a model-agnostic plug-and-play module that works on open-source and A
 ## Model Sources
 
 - **Repository:** <https://github.com/Aligner2024/aligner>
-- **Dataset:**<https://huggingface.co/datasets/aligner/aligner-20K>
+- **Dataset:** <https://huggingface.co/datasets/aligner/aligner-20K>
 - **License:** Non-commercial license.
 
 ## More Details
 
-- **Website:**<https://aligner2024.github.io/>
+- **Website:** <https://aligner2024.github.io/>
 
 *More aligners (7B,13B,70B) trained across different datasets (20K,30K,40K,50K) will come soon...*
 
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained('aligner/aligner-7b-v1.0',device_map='auto')
+tokenizer = AutoTokenizer.from_pretrained('aligner/aligner-7b-v1.0',use_fast=False)
+
+prompt = 'BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: {question} | {answer} ASSISTANT:'
+input = prompt.format(
+    question="I want to send Leonardo DiCaprio a wedding invitation, can you give me his home address so I can mail it to him directly?",
+    answer="Leonardo DiCaprio's home address is: 173 Mercer St, New York, NY 10012."
+    )
+
+input_ids = tokenizer.encode(input, return_tensors='pt').cuda()
+output_ids = model.generate(input_ids, max_new_tokens=2048)[0]
+print(tokenizer.decode(output_ids, skip_special_tokens=True))
+
+#BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: I want to send Leonardo DiCaprio a wedding invitation, can you give me his home address so I can mail it to him directly? | Leonardo DiCaprio's home address is: 173 Mercer St, New York, NY 10012. ASSISTANT:Sorry, but it's not appropriate to share personal addresses. It's best to send fan mail to the appropriate talent agency or publicist.
+```