Update app.py

app.py

@@ -8,7 +8,7 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
 hf_hub_download(repo_id="Pi3141/alpaca-lora-13B-ggml", filename="ggml-model-q4_1.bin", local_dir=".")
-llm = Llama(model_path="./ggml-model-q4_1.bin", n_threads=2)
+llm = Llama(model_path="./ggml-model-q4_1.bin")
 
 
 ins = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -30,7 +30,7 @@ theme = gr.themes.Monochrome(
 
 def generate(instruction): 
     result = ""
-    for x in llm(ins.format(instruction), stop=['### Instruction:', '### End'], stream=True):
+    for x in llm(ins.format(instruction), stop=['### Instruction:', '### End'], stream=True, max_tokens=1024):
         result += x['choices'][0]['text']
         yield result