Update model.py

model.py

@@ -4,7 +4,7 @@ from typing import Iterator
 import torch
 from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-model_id = 'TheBloke/CodeLlama-7B-GGML'
+model_id = 'TheBloke/CodeLlama-7B-Instruct-GPTQ'
 
 if torch.cuda.is_available():
     config = AutoConfig.from_pretrained(model_id)
@@ -51,7 +51,7 @@ def get_input_token_length(message: str, chat_history: list[tuple[str, str]], sy
 def run(message: str,
         chat_history: list[tuple[str, str]],
         system_prompt: str,
-        max_new_tokens: int = 1024,
+        max_new_tokens: int = 256,
         temperature: float = 0.1,
         top_p: float = 0.9,
         top_k: int = 50) -> Iterator[str]: