Update README.md

README.md

@@ -28,6 +28,33 @@ More information needed
 
 More information needed
 
+## How to use model
+
+1. Loading the model
+
+'''python
+import torch
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+# Load peft config for pre-trained checkpoint etc. 
+peft_model_id = "emonty777/QLoRA-Flan-T5-Small"
+
+config = PeftConfig.from_pretrained(peft_model_id)
+
+# load base LLM model and tokenizer / runs on CPU
+model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path)
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# load base LLM model and tokenizer for GPU
+model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path,  load_in_8bit=True,  device_map={"":0})
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# Load the Lora model
+model = PeftModel.from_pretrained(model, peft_model_id, device_map={"":0})
+model.eval()
+'''
+
 ## Training procedure
 
 ### Training hyperparameters