Update app.py

app.py

@@ -4,7 +4,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 from threading import Thread
 
-model_path = 'sail/Sailor-7B-Chat'
+model_path = 'infly/OpenCoder-8B-Instruct'
 
 # Loading the tokenizer and model from Hugging Face's model hub.
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
@@ -17,7 +17,7 @@ model = model.to(device)
 # Defining a custom stopping criteria class for the model's text generation.
 class StopOnTokens(StoppingCriteria):
     def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
-        stop_ids = [151645]  # IDs of tokens where the generation should stop.
+        stop_ids = [96539]  # IDs of tokens where the generation should stop.
         for stop_id in stop_ids:
             if input_ids[0][-1] == stop_id:  # Checking if the last generated token is a stop token.
                 return True