From 980f8112a7d04c974ed5d47e52a8f252b9557fc1 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Mon, 9 Jan 2023 12:56:54 -0300
Subject: [PATCH] Small bug fix

---
 server.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/server.py b/server.py
index 588408d0..4d349249 100644
--- a/server.py
+++ b/server.py
@@ -103,7 +103,7 @@ def generate_reply(question, temperature, max_length, inference_settings, select
     if eos_token is None:
         output = eval(f"model.generate(input_ids, {preset}){cuda}")
     else:
-        n = tokenizer.encode(eos_token, return_tensors='pt')[0][1]
+        n = tokenizer.encode(eos_token, return_tensors='pt')[0][-1]
         output = eval(f"model.generate(input_ids, eos_token_id={n}, {preset}){cuda}")
 
     reply = tokenizer.decode(output[0], skip_special_tokens=True)
@@ -131,6 +131,7 @@ else:
             print(f"{i+1}. {model}")
         print(f"\nWhich one do you want to load? 1-{len(available_models)}\n")
         i = int(input())-1
+        print()
     model_name = available_models[i]
 model, tokenizer = load_model(model_name)