Update tiny models for MllamaModel

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,90 @@
+{
+  "architectures": [
+    "MllamaModel"
+  ],
+  "dtype": "float32",
+  "image_token_index": 4,
+  "model_type": "mllama",
+  "text_config": {
+    "bos_token_id": 128000,
+    "cross_attention_layers": [
+      1
+    ],
+    "dropout": 0.0,
+    "eos_token_id": 128001,
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "max_position_embeddings": 512,
+    "model_type": "mllama_text_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 4,
+    "pad_token_id": 128004,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "rope_theta": 500000.0,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 128257
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_heads": 4,
+    "dropout": 0.1,
+    "hidden_act": "gelu",
+    "hidden_size": 16,
+    "image_size": 30,
+    "initializer_range": 0.02,
+    "intermediate_layers_indices": [
+      0
+    ],
+    "intermediate_size": 37,
+    "max_num_tiles": 4,
+    "model_type": "mllama_vision_model",
+    "norm_eps": 1e-05,
+    "num_channels": 3,
+    "num_global_layers": 2,
+    "num_hidden_layers": 2,
+    "patch_size": 2,
+    "projection_dim": 32,
+    "supported_aspect_ratios": [
+      [
+        1,
+        1
+      ],
+      [
+        1,
+        2
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        1,
+        4
+      ],
+      [
+        2,
+        1
+      ],
+      [
+        2,
+        2
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        4,
+        1
+      ]
+    ],
+    "vision_output_dim": 32
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9093b3096db33cbda4578a82c70dd380ad5a38903ef68a19a2311211ff6ad1ad
+size 17073220

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "MllamaImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_tiles": 4,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 30,
+    "width": 30
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9816d43bd5347d64bccc66b7710947fb18e9818cc660215b1462061d4a44e449
+size 17210088

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}