Update README.md

README.md

@@ -96,7 +96,7 @@ def generate_prompt(instruction: str, input_ctxt: str = None) -> str:
 
 Use the code below to get started with the model.
 
-1. You can directly call the model from HuggingFace using the following code snippet:
+1. You can git clone the repo, which contains also the artifacts for the base model for simplicity and completeness, and run the following code snippet to load the mode:
 
 ```python
 import torch
@@ -104,12 +104,14 @@ from peft import PeftConfig, PeftModel
 from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM
 
 MODEL_NAME = "Sandiago21/llama-13b-hf-prompt-answering"
-BASE_MODEL = "decapoda-research/llama-13b-hf"
 
 config = PeftConfig.from_pretrained(MODEL_NAME)
 
+# Setting the path to look at your repo directory, assuming that you are at that directory when running this script
+config.base_model_name_or_path = "decapoda-research/llama-7b-hf/"
+
 model = LlamaForCausalLM.from_pretrained(
-    BASE_MODEL,
+    config.base_model_name_or_path,
     load_in_8bit=True,
     torch_dtype=torch.float16,
     device_map="auto",
@@ -155,7 +157,7 @@ print(response)
 >>> The capital city of Greece is Athens and it borders Turkey, Bulgaria, Macedonia, Albania, and the Aegean Sea.
 ```
 
-1. You can git clone the repo, which contains also the artifacts for the base model for simplicity and completeness, and run the following code snippet to load the mode:
+2. You can directly call the model from HuggingFace using the following code snippet:
 
 ```python
 import torch
@@ -163,11 +165,12 @@ from peft import PeftConfig, PeftModel
 from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM
 
 MODEL_NAME = "Sandiago21/llama-13b-hf-prompt-answering"
+BASE_MODEL = "decapoda-research/llama-13b-hf"
 
 config = PeftConfig.from_pretrained(MODEL_NAME)
 
 model = LlamaForCausalLM.from_pretrained(
-    config.base_model_name_or_path,
+    BASE_MODEL,
     load_in_8bit=True,
     torch_dtype=torch.float16,
     device_map="auto",