Update

app.py

@@ -9,7 +9,7 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-DESCRIPTION = "# Mistral-7B"
+DESCRIPTION = "# Mistral-7B v0.2"
 
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
@@ -19,7 +19,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available():
-    model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+    model_id = "mistralai/Mistral-7B-Instruct-v0.2"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
@@ -45,7 +45,7 @@ def generate(
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,