Update app.py

app.py

@@ -6,17 +6,14 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download #load from huggingfaces 
 
 
-llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/airoboros-l2-13b-gpt4-m2.0-GGML", filename="airoboros-l2-13b-gpt4-m2.0.ggmlv3.q6_K.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
+llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/Vigogne-2-7B-Chat-GGML", filename="vigogne-2-7b-chat.ggmlv3.q4_1.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
 
 history = []
 
 def generate_text(input_text, history):
     print("history ",history)
     print("input ", input_text)
-    full_conversation = f"{full_conversation[-1]} Q: {input_text} \n A:"
-    print("full convo", full_conversation)
-
-    output = llm(full_conversation, max_tokens=1024, stop=["Q:", "\n"], echo=True)
+    output = llm(input_text, max_tokens=1024, stop=["Q:", "\n"], echo=True)
     response = output['choices'][0]['text']
     return response