Update tiny models for LightOnOcrModel

.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.jinja

@@ -0,0 +1,26 @@
+{% set image_count = namespace(value=0) %}
+{% for message in messages %}
+{% if loop.first and message['role'] != 'system' %}
+<|im_start|>system<|im_end|>
+{% endif %}
+<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}
+{{ message['content'] }}<|im_end|>
+{% else %}
+{% for content in message['content'] %}
+{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}
+{% set image_count.value = image_count.value + 1 %}
+{% if add_vision_id %}
+Picture {{ image_count.value }}:
+{% endif -%}
+<|image_pad|>
+{%- elif 'text' in content %}
+{{ content['text'] }}
+{% endif %}
+{% endfor %}
+<|im_end|>
+{% endif %}
+{% endfor %}
+{% if add_generation_prompt %}
+<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,82 @@
+{
+  "architectures": [
+    "LightOnOcrModel"
+  ],
+  "dtype": "float32",
+  "image_token_id": 10,
+  "model_type": "lighton_ocr",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": 0,
+    "eos_token_id": 151645,
+    "head_dim": 8,
+    "hidden_act": "silu",
+    "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
+    },
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 512,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 4,
+    "num_choices": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "seq_length": 7,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "type_sequence_label_size": 2,
+    "type_vocab_size": 16,
+    "use_cache": true,
+    "use_input_mask": true,
+    "use_labels": true,
+    "use_sliding_window": false,
+    "use_token_type_ids": false,
+    "vocab_size": 151669
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 8,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "image_size": 112,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_training": true,
+    "model_type": "pixtral",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932e3cdf736eb9d803f280908fda73bb29cc5754eab9e265ae147e28b25c89c2
+size 19634904

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "crop_size": {
+    "longest_edge": 112,
+    "shortest_edge": 112
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 112,
+    "shortest_edge": 112
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_break_token": "<|vision_pad|>",
+  "image_end_token": "<|vision_end|>",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "image_break_token": "<|vision_pad|>",
+    "image_end_token": "<|vision_end|>",
+    "image_token": "<|image_pad|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "processor_class": "LightOnOCRProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}