Update tiny models for ColPaliForRetrieval

.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 +1,161 @@
+{
+  "architectures": [
+    "ColPaliForRetrieval"
+  ],
+  "dtype": "float32",
+  "embedding_dim": 128,
+  "model_type": "colpali",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": 2,
+    "eos_token_id": 1,
+    "head_dim": 8,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_training": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "max_position_embeddings": 512,
+    "model_type": "gemma",
+    "num_attention_heads": 4,
+    "num_choices": 4,
+    "num_hidden_layers": 2,
+    "num_image_tokens": 16,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "seq_length": 128,
+    "tie_word_embeddings": true,
+    "type_sequence_label_size": 2,
+    "type_vocab_size": 16,
+    "use_bidirectional_attention": true,
+    "use_cache": true,
+    "use_labels": true,
+    "use_token_type_ids": false,
+    "vocab_size": 257153
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vlm_config": {
+    "hidden_size": 2048,
+    "ignore_index": -100,
+    "image_token_index": 0,
+    "model_type": "paligemma",
+    "projection_dim": 32,
+    "projector_hidden_act": "gelu",
+    "text_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "attention_probs_dropout_prob": 0.1,
+      "bos_token_id": 2,
+      "chunk_size_feed_forward": 0,
+      "dtype": null,
+      "eos_token_id": 1,
+      "head_dim": 8,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_activation": "gelu_pytorch_tanh",
+      "hidden_dropout_prob": 0.1,
+      "hidden_size": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1",
+        "2": "LABEL_2"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 37,
+      "is_encoder_decoder": false,
+      "is_training": true,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1,
+        "LABEL_2": 2
+      },
+      "max_position_embeddings": 512,
+      "model_type": "gemma",
+      "num_attention_heads": 4,
+      "num_choices": 4,
+      "num_hidden_layers": 2,
+      "num_image_tokens": 16,
+      "num_key_value_heads": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": 0,
+      "problem_type": null,
+      "return_dict": true,
+      "rms_norm_eps": 1e-06,
+      "rope_parameters": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      },
+      "seq_length": 128,
+      "tie_word_embeddings": true,
+      "type_sequence_label_size": 2,
+      "type_vocab_size": 16,
+      "use_bidirectional_attention": true,
+      "use_cache": true,
+      "use_labels": true,
+      "use_token_type_ids": false,
+      "vocab_size": 257153
+    },
+    "tie_word_embeddings": true,
+    "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": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 20,
+      "initializer_range": 0.02,
+      "intermediate_size": 37,
+      "is_encoder_decoder": false,
+      "is_training": true,
+      "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,
+      "num_image_tokens": 4,
+      "num_key_value_heads": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "patch_size": 5,
+      "problem_type": null,
+      "projection_dim": 32,
+      "return_dict": true,
+      "use_labels": true
+    },
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "default",
+    "vocab_size": 257152
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d046545c418368bf5e86d5fe10036d4ed2f934d9e33094ea3b530ecc7fd334
+size 33088132

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 1024,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0719264e920323136a27a14fbed84870f400c3d91dab7e813deba64d639fb8f
+size 34600974

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<image>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "max_length": 50,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "PaliGemmaProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}