fix(config): Set eos/bos to tokenizer if different (axolotl-ai-cloud#801

) * fix(config): Set eos/bos to tokenizer if different * chore: fix lint
mkeoliya · Oct 29, 2023 · 874d485 · 874d485
1 parent ae306fb
commit 874d485
Showing 1 changed file with 14 additions and 0 deletions.
diff --git a/src/axolotl/utils/models.py b/src/axolotl/utils/models.py
@@ -386,6 +386,20 @@ 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)