diff --git a/gitbook/README.md b/gitbook/README.md
index 5c4b4d58a..642bde22a 100644
--- a/gitbook/README.md
+++ b/gitbook/README.md
@@ -1,2 +1 @@
 # Page
-
diff --git a/src/axolotl/utils/models.py b/src/axolotl/utils/models.py
index d907a194b..2fbbea6c1 100644
--- a/src/axolotl/utils/models.py
+++ b/src/axolotl/utils/models.py
@@ -406,6 +406,20 @@ def load_model(
         )
         model.config.max_position_embeddings = cfg.sequence_len
 
+    if (
+        hasattr(model.config, "bos_token_id")
+        and model.config.bos_token_id
+        and model.config.bos_token_id != tokenizer.bos_token_id
+    ):
+        model.config.bos_token_id = tokenizer.bos_token_id
+
+    if (
+        hasattr(model.config, "eos_token_id")
+        and model.config.eos_token_id
+        and model.config.eos_token_id != tokenizer.eos_token_id
+    ):
+        model.config.eos_token_id = tokenizer.eos_token_id
+
     if model.device.type == "cuda":
         log_gpu_memory_usage(LOG, "after model load", model.device)