Update src/llama_call.py

src/llama_call.py

@@ -27,13 +27,17 @@ PROMPT = PromptTemplate(
 chain_type_kwargs = {"prompt": PROMPT}
 
 current_dir = os.getcwd()
-llm = CTransformers(
-    model=os.path.join(current_dir, "saved_models/llama-2-7b-chat.ggmlv3.q4_0.bin"),
-    model_type="llama",
-    streaming=True,
-    config={"max_new_tokens": 256, "temperature": 0.6, "context_length": -1},
-)
 
+def load_llm():
+    llm = CTransformers(
+        model="TheBloke/Llama-2-7B-Chat-GGML",
+        model_type="llama",
+        max_new_tokens=512,
+        temperature=0.5
+    )
+    return llm
+    
+llm = load_llm()
 
 qa = RetrievalQA.from_chain_type(
     llm=llm,