Update tiny models for ColModernVBertForRetrieval

chat_template.jinja

@@ -0,0 +1,2 @@
+<|begin_of_text|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
+{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}

config.json

@@ -0,0 +1,122 @@
+{
+  "architectures": [
+    "ColModernVBertForRetrieval"
+  ],
+  "dtype": "float32",
+  "embedding_dim": 64,
+  "initializer_range": 0.02,
+  "model_type": "colmodernvbert",
+  "transformers_version": "5.16.0.dev0",
+  "vlm_config": {
+    "classifier_bias": false,
+    "classifier_dropout": 0.0,
+    "classifier_pooling": "cls",
+    "image_token_id": 98,
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "model_type": "modernvbert",
+    "pixel_shuffle_factor": 2,
+    "text_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bos_token_id": 50281,
+      "chunk_size_feed_forward": 0,
+      "classifier_activation": "gelu",
+      "classifier_bias": false,
+      "classifier_dropout": 0.1,
+      "classifier_pooling": "cls",
+      "cls_token_id": 50281,
+      "decoder_bias": true,
+      "deterministic_flash_attn": false,
+      "dtype": null,
+      "embedding_dropout": 0.1,
+      "eos_token_id": 50282,
+      "hidden_activation": "gelu",
+      "hidden_size": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_cutoff_factor": 2.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 64,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "full_attention",
+        "sliding_attention"
+      ],
+      "local_attention": 128,
+      "max_position_embeddings": 512,
+      "mlp_bias": false,
+      "mlp_dropout": 0.1,
+      "model_type": "modernbert",
+      "norm_bias": false,
+      "norm_eps": 1e-05,
+      "num_attention_heads": 2,
+      "num_hidden_layers": 2,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": 0,
+      "problem_type": null,
+      "return_dict": true,
+      "rope_parameters": {
+        "full_attention": {
+          "rope_theta": 160000.0,
+          "rope_type": "default"
+        },
+        "sliding_attention": {
+          "rope_theta": 10000.0,
+          "rope_type": "default"
+        }
+      },
+      "sep_token_id": 50282,
+      "sparse_pred_ignore_index": -100,
+      "sparse_prediction": false,
+      "tie_word_embeddings": true,
+      "type_vocab_size": 2,
+      "vocab_size": 99
+    },
+    "tie_word_embeddings": false,
+    "vision_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_dropout": 0.1,
+      "chunk_size_feed_forward": 0,
+      "dropout": 0.1,
+      "dtype": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 64,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 16,
+      "initializer_range": 0.02,
+      "intermediate_size": 32,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "model_type": "siglip_vision_model",
+      "num_attention_heads": 4,
+      "num_channels": 3,
+      "num_hidden_layers": 2,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "patch_size": 4,
+      "problem_type": null,
+      "return_dict": true,
+      "vision_use_head": false
+    },
+    "vocab_size": 99
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d71c8c1139ed2b5c184372e67b30ad3d561a8341dac34ac79b5569f6319540
+size 328336

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Idefics3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_size": {
+    "longest_edge": 512
+  },
+  "resample": 1,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 2048
+  }
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
+  ],
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask",
+    "pixel_values",
+    "pixel_attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "processor_class": "ColModernVBertProcessor",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}