Update app.py

app.py

@@ -10,7 +10,6 @@ from huggingface_hub import hf_hub_download
 hf_hub_download(repo_id="LLukas22/gpt4all-lora-quantized-ggjt", filename="ggjt-model.bin", local_dir=".")
 llm = Llama(model_path="./ggjt-model.bin")
 
-
 ins = '''### Instruction:
 {}
 ### Response:
@@ -24,22 +23,10 @@ theme = gr.themes.Monochrome(
     font=[gr.themes.GoogleFont("Open Sans"), "ui-sans-serif", "system-ui", "sans-serif"],
 )
 
-
-
-
-# def generate(instruction): 
-#     response = llm(ins.format(instruction))
-#     response = response['choices'][0]['text']
-#     result = ""
-#     for word in response.split(" "):
-#         result += word + " "
-#         yield result
-
 def generate(instruction): 
-    result = ""
-    for x in llm(ins.format(instruction), stop=['### Instruction:', '### End'], stream=True):
-        result += x['choices'][0]['text']
-        yield result
+    response = llm(ins.format(instruction), stop=['### Instruction:', '### End'])
+    result = response['choices'][0]['text']
+    return result
 
 
 examples = [