Update app.py

app.py

@@ -1,14 +1,4 @@
-import optimum
-import transformers
-from transformers import AutoConfig, AutoTokenizer, AutoModel, AutoModelForCausalLM
-
-import torch
-import gradio as gr
-import json
-import os
-import shutil
-import requests
-
+model_name = "berkeley-nest/Starling-LM-7B-alpha"
 
 title = "👋🏻Welcome to Tonic's 💫🌠Starling 7B"
 description = "You can use [💫🌠Starling 7B](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) or duplicate it for local use or on Hugging Face! [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
@@ -23,7 +13,15 @@ examples = [
     ]
 ]
 
-model_name = "berkeley-nest/Starling-LM-7B-alpha"
+
+import transformers
+from transformers import AutoConfig, AutoTokenizer, AutoModel, AutoModelForCausalLM
+import torch
+import gradio as gr
+import json
+import os
+import shutil
+import requests
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 temperature=0.4
@@ -31,7 +29,6 @@ max_new_tokens=240
 top_p=0.92
 repetition_penalty=1.7
 
-
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
     device_map="auto",