Update README.md

README.md

@@ -28,8 +28,15 @@ Q: "Please explain the allegory of the cave to me."
 To load the model, you can apply the adapter straight to the original base model: 
 
 ```python
+!pip install -q -U git+https://github.com/huggingface/peft.git
+!pip install -q -U bitsandbytes
+
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from peft import PeftModel
+from huggingface_hub import notebook_login
+
+# notebook_login() # You may need to log in to HuggingFace to download the Mistral model
 
 base_model_id = "mistralai/Mistral-7B-Instruct-v0.3"
 bnb_config = BitsAndBytesConfig(
@@ -48,12 +55,14 @@ base_model = AutoModelForCausalLM.from_pretrained(
 
 tokenizer = AutoTokenizer.from_pretrained(base_model_id, add_bos_token=True, trust_remote_code=True)
 
-prompt = "Please explain the allegory of the cave to me."
-model_input = eval_tokenizer(prompt, return_tensors="pt").to("cuda")
-
+ft_model = PeftModel.from_pretrained(base_model, "LeonardPuettmann/PhiloMistral-7B-Instruct-v0.3")
 ft_model.eval()
+
+prompt = "What is the nature of the self? Is there a soul?"
+model_input = tokenizer(prompt, return_tensors="pt").to("cuda")
+
 with torch.no_grad():
-    print(eval_tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=256, repetition_penalty=1.15)[0], skip_special_tokens=True))
+    print(tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=256, repetition_penalty=1.15)[0], skip_special_tokens=True))
 ```