Add tiny processor fixture for testing

.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

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "rhymes-ai/Aria",
+  "architectures": [
+    "AriaForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "modeling_aria.AriaConfig",
+    "AutoModelForCausalLM": "modeling_aria.AriaForConditionalGeneration"
+  },
+  "ignore_index": -100,
+  "image_token_index": 9,
+  "initializer_range": 0.02,
+  "model_type": "aria",
+  "pad_token_id": 2,
+  "projector_patch_to_query_dict": {
+    "1225": 128,
+    "4900": 256
+  },
+  "text_config": {
+    "hidden_size": 2560,
+    "intermediate_size": 13568,
+    "max_position_embeddings": 65536,
+    "model_type": "aria_text_model",
+    "moe_intermediate_size": 1664,
+    "moe_num_experts": 64,
+    "moe_topk": 6,
+    "num_attention_heads": 20,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 20,
+    "rope_theta": 5000000,
+    "vocab_size": 100352
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0.dev0",
+  "vision_config": {
+    "_flash_attn_2_enabled": true,
+    "architectures": [
+      "AriaVisionModel"
+    ],
+    "attention_heads": 16,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "idefics3_vision",
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_feature_layer": -1,
+  "vocab_size": 617
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.47.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,103 @@
+{
+  "_transform": null,
+  "auto_map": {
+    "AutoImageProcessor": "rhymes-ai/Aria--vision_processor.AriaVisionProcessor",
+    "AutoProcessor": "rhymes-ai/Aria--processing_aria.AriaProcessor"
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "AriaImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_size": 980,
+  "min_image_size": 336,
+  "processor_class": "AriaProcessor",
+  "resample": 3,
+  "split_image": false,
+  "split_resolutions": [
+    [
+      490,
+      980
+    ],
+    [
+      490,
+      1470
+    ],
+    [
+      490,
+      1960
+    ],
+    [
+      490,
+      2450
+    ],
+    [
+      490,
+      2940
+    ],
+    [
+      490,
+      3430
+    ],
+    [
+      490,
+      3920
+    ],
+    [
+      980,
+      1960
+    ],
+    [
+      980,
+      1470
+    ],
+    [
+      980,
+      980
+    ],
+    [
+      980,
+      490
+    ],
+    [
+      1470,
+      490
+    ],
+    [
+      1470,
+      980
+    ],
+    [
+      1960,
+      490
+    ],
+    [
+      1960,
+      980
+    ],
+    [
+      2450,
+      490
+    ],
+    [
+      2940,
+      490
+    ],
+    [
+      3430,
+      490
+    ],
+    [
+      3920,
+      490
+    ]
+  ]
+}

processor_config.json

@@ -0,0 +1,7 @@
+{
+  "processor_class": "AriaProcessor",
+  "size_conversion": {
+    "490": 128,
+    "980": 256
+  }
+}