Add tiny processor fixture for testing

config.json

@@ -0,0 +1,124 @@
+{
+  "architectures": [
+    "Florence2ForConditionalGeneration"
+  ],
+  "dtype": "float16",
+  "image_token_id": 51289,
+  "is_encoder_decoder": true,
+  "model_type": "florence2",
+  "text_config": {
+    "activation_dropout": 0.1,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_final_layer_norm": false,
+    "attention_dropout": 0.1,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.0,
+    "d_model": 768,
+    "decoder_attention_heads": 12,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "dropout": 0.1,
+    "early_stopping": true,
+    "encoder_attention_heads": 12,
+    "encoder_ffn_dim": 3072,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
+    "forced_bos_token_id": 0,
+    "gradient_checkpointing": false,
+    "init_std": 0.02,
+    "max_position_embeddings": 1024,
+    "model_type": "bart",
+    "no_repeat_ngram_size": 3,
+    "normalize_before": false,
+    "num_beams": 3,
+    "num_hidden_layers": 6,
+    "scale_embedding": false,
+    "use_cache": true,
+    "vocab_size": 51328
+  },
+  "transformers_version": "4.56.1",
+  "vision_config": {
+    "activation_function": "gelu",
+    "depths": [
+      1,
+      1,
+      9,
+      1
+    ],
+    "dim_embed": [
+      128,
+      256,
+      512,
+      1024
+    ],
+    "drop_path_rate": 0.1,
+    "embed_dim": [
+      128,
+      256,
+      512,
+      1024
+    ],
+    "enable_checkpoint": false,
+    "image_feature_source": [
+      "spatial_avg_pool",
+      "temporal_avg_pool"
+    ],
+    "image_pos_embed": {
+      "max_pos_embeddings": 50,
+      "type": "learned_abs_2d"
+    },
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "max_pos_embeddings": 50,
+    "max_position_embeddings": 50,
+    "max_temporal_embeddings": 100,
+    "mlp_ratio": 4.0,
+    "model_type": "florence_vision",
+    "num_groups": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "patch_padding": [
+      3,
+      1,
+      1,
+      1
+    ],
+    "patch_prenorm": [
+      false,
+      true,
+      true,
+      true
+    ],
+    "patch_size": [
+      7,
+      3,
+      3,
+      3
+    ],
+    "patch_stride": [
+      4,
+      2,
+      2,
+      2
+    ],
+    "projection_dim": 768,
+    "qkv_bias": true,
+    "visual_temporal_embedding": {
+      "max_temporal_embeddings": 100,
+      "type": "COSINE"
+    },
+    "window_size": 12
+  },
+  "vocab_size": 501
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.56.1"
+}

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_florence2.Florence2Processor"
+  },
+  "crop_size": {
+    "height": 768,
+    "width": 768
+  },
+  "do_center_crop": false,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_seq_length": 577,
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "processor_class": "Florence2Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

processor_config.json

@@ -0,0 +1,120 @@
+{
+  "num_additional_image_tokens": 0,
+  "post_processor_config": {
+    "bboxes": {},
+    "description_with_bboxes": {},
+    "description_with_bboxes_or_polygons": {},
+    "description_with_polygons": {},
+    "ocr": {
+      "area_threshold": 0.0,
+      "pattern": "(.+?)<loc_(\\d+)><loc_(\\d+)><loc_(\\d+)><loc_(\\d+)><loc_(\\d+)><loc_(\\d+)><loc_(\\d+)><loc_(\\d+)>"
+    },
+    "phrase_grounding": {
+      "banned_grounding_tokens": [
+        "it",
+        "I",
+        "me",
+        "mine",
+        "you",
+        "your",
+        "yours",
+        "he",
+        "him",
+        "his",
+        "she",
+        "her",
+        "hers",
+        "they",
+        "them",
+        "their",
+        "theirs",
+        "one",
+        "oneself",
+        "we",
+        "us",
+        "our",
+        "ours",
+        "you",
+        "your",
+        "yours",
+        "they",
+        "them",
+        "their",
+        "theirs",
+        "mine",
+        "yours",
+        "his",
+        "hers",
+        "its",
+        "ours",
+        "yours",
+        "theirs",
+        "myself",
+        "yourself",
+        "himself",
+        "herself",
+        "itself",
+        "ourselves",
+        "yourselves",
+        "themselves",
+        "this",
+        "that",
+        "these",
+        "those",
+        "who",
+        "whom",
+        "whose",
+        "which",
+        "what",
+        "who",
+        "whom",
+        "whose",
+        "which",
+        "that",
+        "all",
+        "another",
+        "any",
+        "anybody",
+        "anyone",
+        "anything",
+        "each",
+        "everybody",
+        "everyone",
+        "everything",
+        "few",
+        "many",
+        "nobody",
+        "none",
+        "one",
+        "several",
+        "some",
+        "somebody",
+        "someone",
+        "something",
+        "each other",
+        "one another",
+        "myself",
+        "yourself",
+        "himself",
+        "herself",
+        "itself",
+        "ourselves",
+        "yourselves",
+        "themselves",
+        "the image",
+        "image",
+        "images",
+        "the",
+        "a",
+        "an",
+        "a group",
+        "other objects",
+        "lots",
+        "a set"
+      ]
+    },
+    "polygons": {},
+    "pure_text": {}
+  },
+  "processor_class": "Florence2Processor"
+}