Update app.py

app.py

@@ -7,7 +7,7 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-MAX_MAX_NEW_TOKENS = 2048
+MAX_MAX_NEW_TOKENS = 4096
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
@@ -15,19 +15,12 @@ DESCRIPTION = """\
 # Gemma 2B on GPU
 """
 
-LICENSE = """
-<p/>
----
-As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta,
-this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
-"""
-
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 
 if torch.cuda.is_available():
-    model_id = "teknium/OpenHermes-2.5-Mistral-7B"
+    model_id = "Nexusflow/Starling-LM-7B-beta"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
@@ -39,7 +32,7 @@ def generate(
     chat_history: list[tuple[str, str]],
     system_prompt: str,
     max_new_tokens: int = 1024,
-    temperature: float = 0.6,
+    temperature: float = 0.5,
     top_p: float = 0.9,
     top_k: int = 50,
     repetition_penalty: float = 1.2,