Add Cosmos3 Edge processor test fixture

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message['role'] + ': ' }}{% for content in message['content'] %}{% if content['type'] == 'image' %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' %}<|vision_start|><|video_pad|><|vision_end|>{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endfor %}{% if add_generation_prompt %}{{ 'assistant: ' }}{% endif %}

processor_config.json

@@ -0,0 +1,59 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Cosmos3EdgeImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 9216,
+      "shortest_edge": 1024
+    }
+  },
+  "processor_class": "Cosmos3EdgeProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": true,
+    "size": {
+      "longest_edge": 73728,
+      "shortest_edge": 1024
+    },
+    "temporal_patch_size": 1,
+    "video_processor_type": "Cosmos3EdgeVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,134 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 7,
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<unk>": 0,
+      "<pad>": 1,
+      "<bos>": 2,
+      "<eos>": 3,
+      "<|vision_start|>": 4,
+      "<|vision_end|>": 5,
+      "<|image_pad|>": 6,
+      "<|video_pad|>": 7,
+      "lower": 8,
+      "newer": 9,
+      "upper": 10,
+      "older": 11,
+      "longer": 12,
+      "string": 13,
+      "Describe": 14,
+      "this": 15,
+      "user": 16,
+      "assistant": 17
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [],
+  "image_token": "<|image_pad|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Cosmos3EdgeProcessor",
+  "return_mm_token_type_ids": true,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "video_token": "<|video_pad|>",
+  "vision_end_token": "<|vision_end|>",
+  "vision_start_token": "<|vision_start|>"
+}