Upload app.py

app.py

@@ -47,11 +47,17 @@ 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)
 
+    terminators = [
+        tokenizer.eos_token_id,
+        tokenizer.convert_tokens_to_ids("<|eot_id|>")
+    ]
+    
     streamer = TextIteratorStreamer(tokenizer, timeout=300.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,
         max_new_tokens=max_new_tokens,
+        eos_token_id=terminators,
         do_sample=True,
         top_p=top_p,
         top_k=top_k,