Try with 7b

README.md

@@ -9,7 +9,7 @@ app_file: app.py
 pinned: false
 models:
 - sentence-transformers/all-MiniLM-L6-v2
-- daryl149/llama-2-13b-chat-hf
+- daryl149/llama-2-7b-chat-hf
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -21,8 +21,8 @@ from langchain import PromptTemplate, LLMChain
 from langchain.vectorstores import FAISS
 
 
-def get_model(model_name):
-    model_repo = 'daryl149/llama-2-13b-chat-hf'
+def get_model():
+    model_repo = 'daryl149/llama-2-7b-chat-hf'
 
     tokenizer = AutoTokenizer.from_pretrained(model_repo, use_fast=True)
 
@@ -39,7 +39,7 @@ def get_model(model_name):
     return tokenizer,model,max_len
 
 
-tokenizer, model, max_len = get_model("llama2-13b")
+tokenizer, model, max_len = get_model()