Added support for Llama-2

Added support for Llama-2 #235

run_localGPT.py

@@ -192,8 +192,8 @@ def main(device_type, show_sources):
     # load the LLM for generating Natural Language responses
 
     # for HF models
-    model_id = "TheBloke/vicuna-7B-1.1-HF"
-    model_basename = None
+    # model_id = "TheBloke/vicuna-7B-1.1-HF"
+    # model_basename = None
     # model_id = "TheBloke/Wizard-Vicuna-7B-Uncensored-HF"
     # model_id = "TheBloke/guanaco-7B-HF"
     # model_id = 'NousResearch/Nous-Hermes-13b' # Requires ~ 23GB VRAM. Using STransformers
@@ -219,6 +219,9 @@ def main(device_type, show_sources):
     # model_id = "TheBloke/orca_mini_3B-GGML"
     # model_basename = "orca-mini-3b.ggmlv3.q4_0.bin"
 
+    model_id="TheBloke/Llama-2-7B-Chat-GGML"
+    model_basename = "llama-2-7b-chat.ggmlv3.q4_0.bin"
+
     llm = load_model(device_type, model_id=model_id, model_basename=model_basename)
 
     qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)