Llama-2-7B

app.py

@@ -35,8 +35,8 @@ def get_vector_store(target_source_chunks):
     return retriver
 
 def get_conversation_chain(retriever):
-    tokenizer = AutoTokenizer.from_pretrained("red1xe/Llama-2-7B-codeGPT")
-    model = AutoModelForCausalLM.from_pretrained("red1xe/Llama-2-7B-codeGPT")
+    tokenizer = AutoTokenizer.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded")
+    model = AutoModelForCausalLM.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded")
     memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True,)
     chain = RetrievalQA.from_llm(
         llm=model,