Update modeling_bunny_phi3.py

modeling_bunny_phi3.py

@@ -878,11 +878,17 @@ class BunnyMetaForCausalLM(ABC):
         if labels is None:
             labels = torch.full_like(input_ids, IGNORE_INDEX)
 
+        input_ids_temp = input_ids # points to the actual input_ids tensor
+
         # remove the padding using attention_mask -- TODO: double check
         input_ids = [cur_input_ids[cur_attention_mask] for cur_input_ids, cur_attention_mask in
                      zip(input_ids, attention_mask)]
         labels = [cur_labels[cur_attention_mask] for cur_labels, cur_attention_mask in zip(labels, attention_mask)]
 
+        # -- TODO: better implementation?
+        # replace IMAGE_TOKEN_INDEX(-200) with 0 to be compatible with repetition penalty
+        input_ids_temp[input_ids_temp == IMAGE_TOKEN_INDEX] = 0
+
         new_input_embeds = []
         new_labels = []
         cur_image_idx = 0