Update README.md

README.md

@@ -1,3 +1,27 @@
 ---
 license: apache-2.0
 ---
+
+Out repository [flan-alpaca-lora](https://github.com/Reason-Wang/flan-alpaca-lora) contains the details to train flan-t5 with [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) instructions and [low-rank adaptation](https://arxiv.org/abs/2106.09685).
+
+This model is trained with [GPTeacher](https://github.com/teknium1/GPTeacher) instructions (Instruct and Roleplay).
+
+Usage:
+
+```python
+import transformers
+from peft import PeftModel
+
+model_name = "google/flan-t5-large"; peft_model_id = "reasonwang/flan-alpaca-lora-large"
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+base_model = transformers.AutoModelForSeq2SeqLM.from_pretrained(model_name)
+peft_model = PeftModel.from_pretrained(base_model, peft_model_id)
+
+inputs = tokenizer("If you are the president of a developing country, what you will do to make your country better?", return_tensors="pt")
+outputs = peft_model.generate(**inputs, max_length=256, do_sample=True)
+print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
+
+# I will take immediate steps to improve education and infrastructure so that citizens thrive.
+# I will also invest in infrastructure upgrades such as hospitals and electricity distribution lines, as well as encouraging innovation in our resiliency infrastructure.
+# I will also focus on promoting trade and investment between countries, both for economic and cultural benefit.
+```