Update app.py

app.py

@@ -17,17 +17,14 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "Skywork/Skywork-o1-Open-PRM-Qwen-2.5-7B"
+model_id = "gmonsoon/SeaMarco-o1-7B-v1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
     torch_dtype=torch.bfloat16,
 )
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
+
 model.config.sliding_window = 4096
 model.eval()
 
@@ -61,7 +58,6 @@ def generate(
         temperature=temperature,
         num_beams=1,
         repetition_penalty=repetition_penalty,
-        eos_token_id=terminators,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()