diff --git a/src/transformers/models/auto/configuration_auto.py b/src/transformers/models/auto/configuration_auto.py
index 38a768e7c641..a626a6db3698 100644
--- a/src/transformers/models/auto/configuration_auto.py
+++ b/src/transformers/models/auto/configuration_auto.py
@@ -1120,6 +1120,7 @@
         ("wav2vec2-bert", "wav2vec2_bert"),
         ("vibevoice_acoustic_tokenizer_encoder", "vibevoice_acoustic_tokenizer"),
         ("vibevoice_acoustic_tokenizer_decoder", "vibevoice_acoustic_tokenizer"),
+        ('mlcd_vision_model', "mlcd"),
     ]
 )
 
diff --git a/src/transformers/models/auto/image_processing_auto.py b/src/transformers/models/auto/image_processing_auto.py
index 5f607e6e7aa5..a3c3d9ae280c 100644
--- a/src/transformers/models/auto/image_processing_auto.py
+++ b/src/transformers/models/auto/image_processing_auto.py
@@ -228,6 +228,7 @@
             ("vit_msn", ("ViTImageProcessor", "ViTImageProcessorFast")),
             ("vitmatte", ("VitMatteImageProcessor", "VitMatteImageProcessorFast")),
             ("vitpose", ("VitPoseImageProcessor", "VitPoseImageProcessorFast")),
+            ("vivit", ("VivitImageProcessor", None)),
             ("xclip", ("CLIPImageProcessor", "CLIPImageProcessorFast")),
             ("yolos", ("YolosImageProcessor", "YolosImageProcessorFast")),
             ("zoedepth", ("ZoeDepthImageProcessor", "ZoeDepthImageProcessorFast")),
diff --git a/src/transformers/models/auto/modeling_auto.py b/src/transformers/models/auto/modeling_auto.py
index 5a0039fb016b..696675b29c78 100644
--- a/src/transformers/models/auto/modeling_auto.py
+++ b/src/transformers/models/auto/modeling_auto.py
@@ -984,7 +984,7 @@ class _BaseModelWithGenerate(PreTrainedModel, GenerationMixin):
         ("paligemma", "PaliGemmaForConditionalGeneration"),
         ("perception_lm", "PerceptionLMForConditionalGeneration"),
         ("pix2struct", "Pix2StructForConditionalGeneration"),
-        ("pixtral", "LlavaForConditionalGeneration"),
+        ("llava", "LlavaForConditionalGeneration"),
         ("qwen2_5_vl", "Qwen2_5_VLForConditionalGeneration"),
         ("qwen2_vl", "Qwen2VLForConditionalGeneration"),
         ("qwen3_5", "Qwen3_5ForConditionalGeneration"),
@@ -1617,7 +1617,6 @@ class _BaseModelWithGenerate(PreTrainedModel, GenerationMixin):
         # Model for Text-To-Waveform mapping
         ("bark", "BarkModel"),
         ("csm", "CsmForConditionalGeneration"),
-        ("fastspeech2_conformer", "FastSpeech2ConformerWithHifiGan"),
         ("fastspeech2_conformer_with_hifigan", "FastSpeech2ConformerWithHifiGan"),
         ("higgs_audio_v2", "HiggsAudioV2ForConditionalGeneration"),
         ("musicgen", "MusicgenForConditionalGeneration"),
diff --git a/src/transformers/models/evolla/configuration_evolla.py b/src/transformers/models/evolla/configuration_evolla.py
index 227c4407f03d..9194218f6d8b 100644
--- a/src/transformers/models/evolla/configuration_evolla.py
+++ b/src/transformers/models/evolla/configuration_evolla.py
@@ -114,7 +114,7 @@ class EvollaConfig(PreTrainedConfig):
     >>> configuration = model.config
     ```"""
 
-    model_type = "EvollaModel"
+    model_type = "evolla"
     sub_configs = {"protein_encoder_config": SaProtConfig}
     default_theta = 500000.0
 
diff --git a/src/transformers/models/lasr/configuration_lasr.py b/src/transformers/models/lasr/configuration_lasr.py
index 07b57ba4282b..50a85e9e8ebf 100644
--- a/src/transformers/models/lasr/configuration_lasr.py
+++ b/src/transformers/models/lasr/configuration_lasr.py
@@ -59,7 +59,7 @@ class LasrEncoderConfig(PreTrainedConfig):
         ```
 
     This configuration class is based on the LasrEncoder architecture from Google Health AI. You can find more details
-    and pre-trained models at [TODO/TODO](https://huggingface.co/TODO/TODO).
+    and pre-trained models at [google/medasr](https://huggingface.co/google/medasr).
     """
 
     model_type = "lasr_encoder"
@@ -148,7 +148,7 @@ class LasrCTCConfig(PreTrainedConfig):
         >>> configuration = model.config
         ```
     This configuration class is based on the Lasr CTC architecture from Google Health AI. You can find more details
-    and pre-trained models at [TODO/TODO](https://huggingface.co/TODO/TODO).
+    and pre-trained models at [google/medasr](https://huggingface.co/google/medasr).
     """
 
     model_type = "lasr_ctc"