Update tiny models for PaddleOCRVLForConditionalGeneration

.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 +1,43 @@
+{%- if not add_generation_prompt is defined -%}
+    {%- set add_generation_prompt = true -%}
+{%- endif -%}
+{%- if not cls_token is defined -%}
+    {%- set cls_token = "<|begin_of_sentence|>" -%}
+{%- endif -%}
+{%- if not eos_token is defined -%}
+    {%- set eos_token = "</s>" -%}
+{%- endif -%}
+{{- cls_token -}}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {{- "User: " -}}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "image" -%}
+                {{ "<|IMAGE_START|><|IMAGE_PLACEHOLDER|><|IMAGE_END|>" }}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] }}
+            {%- endif -%}
+        {%- endfor -%}
+        {{ "\n" -}}
+    {%- elif message["role"] == "assistant" -%}
+        {{- "Assistant: " -}}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] }}
+            {%- endif -%}
+        {%- endfor -%}
+        {{ eos_token -}}
+    {%- elif message["role"] == "system" -%}
+        {%- for content in message["content"] -%}
+            {%- if content["type"] == "text" -%}
+                {{ content["text"] + "\n" }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "Assistant: " -}}
+{%- endif -%}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "PaddleOCRVLForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_token_id": 100295,
+  "model_type": "paddleocr_vl",
+  "text_config": {
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 32,
+    "ignored_index": -100,
+    "image_token_id": 100295,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "max_position_embeddings": 512,
+    "model_type": "paddleocr_vl_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_theta": 500000,
+      "rope_type": "default",
+      "type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_bias": false,
+    "use_cache": true,
+    "vocab_size": 101314
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "video_token_id": 100296,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 144,
+    "image_size": 384,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "paddleocr_vl_vision",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "patch_size": 14,
+    "spatial_merge_size": 2
+  },
+  "vision_end_token_id": 101306,
+  "vision_start_token_id": 101305
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa51a0628fb3de7602dd3940d5296404199b77ca4b551fb24c4a9725d45aa169
+size 16306528

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "crop_size": {
+    "longest_edge": 384,
+    "shortest_edge": 384
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PaddleOCRVLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "merge_size": 2,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 384,
+    "shortest_edge": 384
+  },
+  "temporal_patch_size": 1
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90f04fd8e5eb6dfa380f37d10c87392de8438dccb6768a2486b5a96ee76dba6
+size 11187679

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "auto_map": {
+    "AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor"
+  },
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<|begin_of_sentence|>",
+  "eos_token": "</s>",
+  "image_token": "<|IMAGE_PLACEHOLDER|>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "mask_token": "<mask:1>",
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "image_token": "<|IMAGE_PLACEHOLDER|>"
+  },
+  "pad_token": "<unk>",
+  "processor_class": "PaddleOCRVLProcessor",
+  "sep_token": "<|end_of_sentence|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}