Update README.md

README.md

@@ -1,3 +1,23 @@
 ---
 license: apache-2.0
 ---
+
+```py
+#https://huggingface.co/docs/peft/quicktour 
+
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+import torch
+
+model = AutoPeftModelForCausalLM.from_pretrained("Sentdex/Walls1337bot-Llama2-7B-003.004.400")
+tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
+
+model = model.to("cuda")
+model.eval()
+
+formatted_prompt = f"### BEGIN CONVERSATION ###\n\n## Speaker_0: ##\n{prompt}\n\n## Walls1337bot: ##\n"
+inputs = tokenizer(formatted_prompt, return_tensors="pt")
+outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=128)
+text_output = 
+print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0])
+```