Yigdzin 1 (v1): grow26-ep2 checkpoint + model card (private test upload)

README.md

@@ -0,0 +1,177 @@
+---
+license: apache-2.0
+base_model: PaddlePaddle/PaddleOCR-VL-1.6
+language:
+- bo
+tags:
+- ocr
+- tibetan
+- vision-language
+- paddleocr-vl
+- pecha
+pipeline_tag: image-text-to-text
+library_name: transformers
+metrics:
+- cer
+---
+
+# Tibetan OCR — Yigdzin 1
+
+<!-- DRAFT model card for BDRC/tibetan-ocr, release tag v1 ("Yigdzin 1").
+     Numbers are PRELIMINARY (v1). Confirm display name sign-off before publishing. -->
+
+**A vision-first OCR model for Tibetan pecha** — modern publications, woodblock
+prints, and manuscripts (uchen and u-med), including pecha layout and orthographic
+shorthands. Built by the [Buddhist Digital Resource Center (BDRC)](https://bdrc.io)
+and trained on ~220k curated real + synthetic pages.
+
+- **Repository:** `BDRC/tibetan-ocr` · release **`v1`** (display name **Yigdzin 1**)
+- **Base model:** [`PaddlePaddle/PaddleOCR-VL-1.6`](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) (Apache-2.0)
+- **Live demo:** [ocr.bdrc.io](https://ocr.bdrc.io) · **Desktop app:** [buda-base/tibetan-ocr-app](https://github.com/buda-base/tibetan-ocr-app)
+
+## TL;DR
+
+On a 1,070-page hand-transcribed benchmark, typical-page character error rate is
+**~1.8% (median CER 0.0179)**; corpus micro-CER is **0.0756** (greedy). It is a
+*specialized* OCR model, not a general chat VLM.
+
+## Model details
+
+| | |
+|---|---|
+| Architecture | PaddleOCR-VL-1.6 (vision encoder + depth-upscaled decoder) |
+| Parameters | ~810M (~413M vision · ~360M 26-layer decoder · ~4M embeddings/head) |
+| Vision share | ~51–59% of parameters ("big eyes, small mouth" — vision-first) |
+| Tokenizer | Tibetan **unicode-stack** tokenizer, vocab **3,560** (pruned + BoCorpus-warmed) |
+| Languages | Tibetan (`bo`); Tibetan script |
+| License | Apache-2.0 (derivative of PaddleOCR-VL-1.6; upstream `NOTICE` retained) |
+| Funder | Khyentse Foundation ("The BDRC Etext Corpus") |
+
+## Intended use
+
+- OCR of Tibetan pecha pages: **uchen** and **u-med** (dbu med) scripts across
+  **modern print, woodblock, and manuscript** sources.
+- Batch OCR at corpus scale (BDRC is applying it to ~25M scanned pages).
+
+**Out of scope:** general vision-language chat / VQA; non-Tibetan scripts; layout
+analysis of illustrations, tables, or diagrams; line/region detection (this model
+transcribes page or line crops it is given).
+
+## How to use
+
+Prompt (used at training and inference), rendered through the repo's
+`chat_template.jinja`:
+
+```
+Extract all Tibetan text. Preserve line breaks.
+```
+
+This checkpoint uses the **native** PaddleOCR-VL architecture (`model_type:
+paddleocr_vl`, `PaddleOCRVLForConditionalGeneration`) — **no `trust_remote_code`
+needed**, but it requires **transformers ≥ 5.15** (native `paddleocr_vl` support)
+or **vLLM ≥ 0.26**. Decode **greedy** (`temperature=0`).
+
+> **⚠ Position regime — required for correct output.** This model was trained in the
+> **sequential** image-token M-RoPE regime (1-D positions), *not* the default "grid"
+> regime. If the processor emits a non-zero `mm_token_type_ids`, structured pages
+> loop badly (some pages regress from ~0.10 to ~0.62 CER). Serve it sequential:
+> - **HF:** zero the mask before the forward —
+>   `inputs["mm_token_type_ids"] = torch.zeros_like(inputs["input_ids"])`.
+> - **vLLM:** install the `vllm_paddleocr_seqpos` plugin and set
+>   `OCR_VLLM_IMAGE_TOKEN_POSITIONS=sequential`.
+
+### HF transformers (reference / accuracy baseline)
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
+model_id = "BDRC/tibetan-ocr"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="bfloat16", device_map="cuda")
+
+image = Image.open("page.jpg").convert("RGB")
+messages = [{"role": "user", "content": [
+    {"type": "image"},
+    {"type": "text", "text": "Extract all Tibetan text. Preserve line breaks."}]}]
+prompt = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+inputs = processor(text=[prompt], images=[image], return_tensors="pt").to("cuda")
+inputs["mm_token_type_ids"] = torch.zeros_like(inputs["input_ids"])  # sequential regime (required)
+out = model.generate(**inputs, do_sample=False, max_new_tokens=4096)
+print(processor.batch_decode(out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0])
+```
+
+### vLLM (production)
+
+Serve greedy (`temperature=0`) with **vLLM ≥ 0.26**. The **only** extra requirement is
+the sequential image-token position regime (above): install the `vllm_paddleocr_seqpos`
+plugin and set `OCR_VLLM_IMAGE_TOKEN_POSITIONS=sequential`. Without it, structured
+pages loop and accuracy collapses.
+
+<!-- The snippets above are the intended native path; run them once on a GPU box
+     against deploy/fast_inference/bench.py (the source-of-truth harness) before
+     publishing, and paste the exact class/kwargs it uses. -->
+
+Legitimate repetitive scripture (mantras, litanies) is real Tibetan text — do not add
+aggressive anti-repetition settings that would "correct" it away.
+
+## Training data
+
+~220k-page curated mix (`bec_mixed_elie_v6`), assembled from BDRC alignment
+collections + BoCorpus-rendered synthetic pages, with an easy→hard curriculum,
+u-med over-weighting, and repetition-aware filtering. Released component datasets:
+
+- Real transcriptions: [ALL-BDRC (ACIP Sungbum)](https://huggingface.co/datasets/BDRC/all-bdrc),
+  [PalriParkhang](https://huggingface.co/datasets/BDRC/palri-parkhang),
+  [Berkeley](https://huggingface.co/datasets/BDRC/berkeley),
+  [MonlamAI-transcriptions](https://huggingface.co/datasets/BDRC/monlamai-transcriptions),
+  [MonlamAI-handwritten](https://huggingface.co/datasets/BDRC/monlamai-handwritten),
+  [Stok](https://huggingface.co/datasets/BDRC/stok), [TibSchol](https://huggingface.co/datasets/BDRC/tibschol) *(gated)*.
+- Synthetic: [Tibetan OCR synthetic v5](https://huggingface.co/datasets/BDRC/tibetan-ocr-synthetic).
+
+<!-- Fill final dataset repo links once created; see the release plan. -->
+
+## Evaluation *(preliminary, v1)*
+
+Evaluated on the BDRC hand-transcribed benchmark `20260315` (1,070 pages), greedy
+decoding, `max_new_tokens=4096`, prompt policy `none`.
+
+| Setting | micro-CER | median CER | hard-loops |
+|---|---:|---:|---:|
+| **Yigdzin 1** (greedy) | **0.0756** | **0.0179** | **2** |
+| PaddleOCR-VL 18-layer baseline (ep1) | 0.1198 | 0.0211 | 16 |
+
+CER = Levenshtein(hyp, ref)/len(ref) after botok normalization, whitespace
+stripping, tsheg folding, and placeholder removal. Full method + the multi-system
+leaderboard: **[BDRC Tibetan OCR benchmark](https://huggingface.co/datasets/BDRC/tibetan-ocr-benchmark)** and the **[leaderboard](https://huggingface.co/spaces/BDRC/tibetan-ocr-leaderboard)**.
+
+## Limitations & recommendations
+
+- **Residual repetition loops** on a small fraction of pages (~0.2% greedy). Keep any
+  anti-loop mitigation gentle: legitimate repetitive scripture (mantras) must not be
+  "corrected" away.
+- **Line-break joins** on some dense (6-line) woodblock pecha (~1.9% of such pages).
+- Struggles on illustrations, non-Tibetan text, and illegible/damaged pages.
+- Metrics are **preliminary (v1)** and may change in later generations.
+
+## Citation
+
+A comprehensive article is forthcoming (Springer *Language Resources and
+Evaluation*). Until then, please cite the model and BDRC:
+
+```bibtex
+@misc{bdrc_tibetan_ocr_2026,
+  title  = {Tibetan OCR (Yigdzin 1)},
+  author = {Roux, Elie and Werner, Eric},
+  year   = {2026},
+  howpublished = {Buddhist Digital Resource Center, Hugging Face},
+  note   = {https://huggingface.co/BDRC/tibetan-ocr}
+}
+```
+
+## Acknowledgements
+
+Built on [PaddleOCR-VL](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6)
+(Apache-2.0). Funded by the **Khyentse Foundation**. Thanks to the BDRC, Dharmaduta,
+and collaborating transcription teams.

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:\n" -}}
+        {%- 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:\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,80 @@
+{
+  "architectures": [
+    "PaddleOCRVLForConditionalGeneration"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "compression_ratio": 1.0,
+  "dtype": "bfloat16",
+  "hidden_dropout_prob": 0.0,
+  "ignored_index": -100,
+  "image_token_id": 2141,
+  "max_sequence_length": null,
+  "model_type": "paddleocr_vl",
+  "rope_is_neox_style": true,
+  "sliding_window": null,
+  "text_config": {
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "max_position_embeddings": 131072,
+    "model_type": "paddleocr_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 26,
+    "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": true,
+    "use_bias": false,
+    "use_cache": false,
+    "vocab_size": 3560
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.2",
+  "use_3d_rope": true,
+  "use_cache": false,
+  "use_flash_attention": false,
+  "video_token_id": 3151,
+  "vision_config": {
+    "architectures": [
+      "PaddleOCRVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
+      "AutoModel": "modeling_paddleocr_vl.PaddleOCRVisionModel"
+    },
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "paddleocr_vl_vision",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "pad_token_id": 0,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2
+  },
+  "vision_end_token_id": 2140,
+  "vision_start_token_id": 2143,
+  "weight_share_add_bias": true
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "5.10.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54eb065005184a30fd17c25e1393e72a457b500045fe510a79221df0af9a34d
+size 1628770560

processor_config.json

@@ -0,0 +1,33 @@
+{
+  "image_processor": {
+    "auto_map": {
+      "AutoImageProcessor": "image_processing_paddleocr_vl.PaddleOCRVLImageProcessor",
+      "AutoProcessor": "processing_paddleocr_vl.PaddleOCRVLProcessor"
+    },
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "PaddleOCRVLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "shortest_edge": 1024,
+      "longest_edge": 1003520
+    },
+    "temporal_patch_size": 1
+  },
+  "processor_class": "PaddleOCRVLProcessor"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9f0fb64c94b09e89e9664c154c94dab86b447d1118b8dc3da64d6e00506558
+size 59509

tokenizer_config.json

@@ -0,0 +1,1053 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<|begin_of_sentence|>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "0",
+    "1",
+    "2",
+    "3",
+    "4",
+    "5",
+    "6",
+    "7",
+    "8",
+    "9",
+    "<ecel>",
+    "<fcel>",
+    "<lcel>",
+    "<mask:4>",
+    "<mask:5>",
+    "<mask:6>",
+    "<mask:7>",
+    "<nl>",
+    "<ucel>",
+    "<xcel>",
+    "<|AUDIO_PLACEHOLDER|>",
+    "<|CROP_COL_SEP|>",
+    "<|CROP_ROW_SEP|>",
+    "<|IMAGE_END|>",
+    "<|IMAGE_PLACEHOLDER|>",
+    "<|IMAGE_SEP|>",
+    "<|IMAGE_START|>",
+    "<|LOC_0|>",
+    "<|LOC_1000|>",
+    "<|LOC_100|>",
+    "<|LOC_101|>",
+    "<|LOC_102|>",
+    "<|LOC_103|>",
+    "<|LOC_104|>",
+    "<|LOC_105|>",
+    "<|LOC_106|>",
+    "<|LOC_107|>",
+    "<|LOC_108|>",
+    "<|LOC_109|>",
+    "<|LOC_10|>",
+    "<|LOC_110|>",
+    "<|LOC_111|>",
+    "<|LOC_112|>",
+    "<|LOC_113|>",
+    "<|LOC_114|>",
+    "<|LOC_115|>",
+    "<|LOC_116|>",
+    "<|LOC_117|>",
+    "<|LOC_118|>",
+    "<|LOC_119|>",
+    "<|LOC_11|>",
+    "<|LOC_120|>",
+    "<|LOC_121|>",
+    "<|LOC_122|>",
+    "<|LOC_123|>",
+    "<|LOC_124|>",
+    "<|LOC_125|>",
+    "<|LOC_126|>",
+    "<|LOC_127|>",
+    "<|LOC_128|>",
+    "<|LOC_129|>",
+    "<|LOC_12|>",
+    "<|LOC_130|>",
+    "<|LOC_131|>",
+    "<|LOC_132|>",
+    "<|LOC_133|>",
+    "<|LOC_134|>",
+    "<|LOC_135|>",
+    "<|LOC_136|>",
+    "<|LOC_137|>",
+    "<|LOC_138|>",
+    "<|LOC_139|>",
+    "<|LOC_13|>",
+    "<|LOC_140|>",
+    "<|LOC_141|>",
+    "<|LOC_142|>",
+    "<|LOC_143|>",
+    "<|LOC_144|>",
+    "<|LOC_145|>",
+    "<|LOC_146|>",
+    "<|LOC_147|>",
+    "<|LOC_148|>",
+    "<|LOC_149|>",
+    "<|LOC_14|>",
+    "<|LOC_150|>",
+    "<|LOC_151|>",
+    "<|LOC_152|>",
+    "<|LOC_153|>",
+    "<|LOC_154|>",
+    "<|LOC_155|>",
+    "<|LOC_156|>",
+    "<|LOC_157|>",
+    "<|LOC_158|>",
+    "<|LOC_159|>",
+    "<|LOC_15|>",
+    "<|LOC_160|>",
+    "<|LOC_161|>",
+    "<|LOC_162|>",
+    "<|LOC_163|>",
+    "<|LOC_164|>",
+    "<|LOC_165|>",
+    "<|LOC_166|>",
+    "<|LOC_167|>",
+    "<|LOC_168|>",
+    "<|LOC_169|>",
+    "<|LOC_16|>",
+    "<|LOC_170|>",
+    "<|LOC_171|>",
+    "<|LOC_172|>",
+    "<|LOC_173|>",
+    "<|LOC_174|>",
+    "<|LOC_175|>",
+    "<|LOC_176|>",
+    "<|LOC_177|>",
+    "<|LOC_178|>",
+    "<|LOC_179|>",
+    "<|LOC_17|>",
+    "<|LOC_180|>",
+    "<|LOC_181|>",
+    "<|LOC_182|>",
+    "<|LOC_183|>",
+    "<|LOC_184|>",
+    "<|LOC_185|>",
+    "<|LOC_186|>",
+    "<|LOC_187|>",
+    "<|LOC_188|>",
+    "<|LOC_189|>",
+    "<|LOC_18|>",
+    "<|LOC_190|>",
+    "<|LOC_191|>",
+    "<|LOC_192|>",
+    "<|LOC_193|>",
+    "<|LOC_194|>",
+    "<|LOC_195|>",
+    "<|LOC_196|>",
+    "<|LOC_197|>",
+    "<|LOC_198|>",
+    "<|LOC_199|>",
+    "<|LOC_19|>",
+    "<|LOC_1|>",
+    "<|LOC_200|>",
+    "<|LOC_201|>",
+    "<|LOC_202|>",
+    "<|LOC_203|>",
+    "<|LOC_204|>",
+    "<|LOC_205|>",
+    "<|LOC_206|>",
+    "<|LOC_207|>",
+    "<|LOC_208|>",
+    "<|LOC_209|>",
+    "<|LOC_20|>",
+    "<|LOC_210|>",
+    "<|LOC_211|>",
+    "<|LOC_212|>",
+    "<|LOC_213|>",
+    "<|LOC_214|>",
+    "<|LOC_215|>",
+    "<|LOC_216|>",
+    "<|LOC_217|>",
+    "<|LOC_218|>",
+    "<|LOC_219|>",
+    "<|LOC_21|>",
+    "<|LOC_220|>",
+    "<|LOC_221|>",
+    "<|LOC_222|>",
+    "<|LOC_223|>",
+    "<|LOC_224|>",
+    "<|LOC_225|>",
+    "<|LOC_226|>",
+    "<|LOC_227|>",
+    "<|LOC_228|>",
+    "<|LOC_229|>",
+    "<|LOC_22|>",
+    "<|LOC_230|>",
+    "<|LOC_231|>",
+    "<|LOC_232|>",
+    "<|LOC_233|>",
+    "<|LOC_234|>",
+    "<|LOC_235|>",
+    "<|LOC_236|>",
+    "<|LOC_237|>",
+    "<|LOC_238|>",
+    "<|LOC_239|>",
+    "<|LOC_23|>",
+    "<|LOC_240|>",
+    "<|LOC_241|>",
+    "<|LOC_242|>",
+    "<|LOC_243|>",
+    "<|LOC_244|>",
+    "<|LOC_245|>",
+    "<|LOC_246|>",
+    "<|LOC_247|>",
+    "<|LOC_248|>",
+    "<|LOC_249|>",
+    "<|LOC_24|>",
+    "<|LOC_250|>",
+    "<|LOC_251|>",
+    "<|LOC_252|>",
+    "<|LOC_253|>",
+    "<|LOC_254|>",
+    "<|LOC_255|>",
+    "<|LOC_256|>",
+    "<|LOC_257|>",
+    "<|LOC_258|>",
+    "<|LOC_259|>",
+    "<|LOC_25|>",
+    "<|LOC_260|>",
+    "<|LOC_261|>",
+    "<|LOC_262|>",
+    "<|LOC_263|>",
+    "<|LOC_264|>",
+    "<|LOC_265|>",
+    "<|LOC_266|>",
+    "<|LOC_267|>",
+    "<|LOC_268|>",
+    "<|LOC_269|>",
+    "<|LOC_26|>",
+    "<|LOC_270|>",
+    "<|LOC_271|>",
+    "<|LOC_272|>",
+    "<|LOC_273|>",
+    "<|LOC_274|>",
+    "<|LOC_275|>",
+    "<|LOC_276|>",
+    "<|LOC_277|>",
+    "<|LOC_278|>",
+    "<|LOC_279|>",
+    "<|LOC_27|>",
+    "<|LOC_280|>",
+    "<|LOC_281|>",
+    "<|LOC_282|>",
+    "<|LOC_283|>",
+    "<|LOC_284|>",
+    "<|LOC_285|>",
+    "<|LOC_286|>",
+    "<|LOC_287|>",
+    "<|LOC_288|>",
+    "<|LOC_289|>",
+    "<|LOC_28|>",
+    "<|LOC_290|>",
+    "<|LOC_291|>",
+    "<|LOC_292|>",
+    "<|LOC_293|>",
+    "<|LOC_294|>",
+    "<|LOC_295|>",
+    "<|LOC_296|>",
+    "<|LOC_297|>",
+    "<|LOC_298|>",
+    "<|LOC_299|>",
+    "<|LOC_29|>",
+    "<|LOC_2|>",
+    "<|LOC_300|>",
+    "<|LOC_301|>",
+    "<|LOC_302|>",
+    "<|LOC_303|>",
+    "<|LOC_304|>",
+    "<|LOC_305|>",
+    "<|LOC_306|>",
+    "<|LOC_307|>",
+    "<|LOC_308|>",
+    "<|LOC_309|>",
+    "<|LOC_30|>",
+    "<|LOC_310|>",
+    "<|LOC_311|>",
+    "<|LOC_312|>",
+    "<|LOC_313|>",
+    "<|LOC_314|>",
+    "<|LOC_315|>",
+    "<|LOC_316|>",
+    "<|LOC_317|>",
+    "<|LOC_318|>",
+    "<|LOC_319|>",
+    "<|LOC_31|>",
+    "<|LOC_320|>",
+    "<|LOC_321|>",
+    "<|LOC_322|>",
+    "<|LOC_323|>",
+    "<|LOC_324|>",
+    "<|LOC_325|>",
+    "<|LOC_326|>",
+    "<|LOC_327|>",
+    "<|LOC_328|>",
+    "<|LOC_329|>",
+    "<|LOC_32|>",
+    "<|LOC_330|>",
+    "<|LOC_331|>",
+    "<|LOC_332|>",
+    "<|LOC_333|>",
+    "<|LOC_334|>",
+    "<|LOC_335|>",
+    "<|LOC_336|>",
+    "<|LOC_337|>",
+    "<|LOC_338|>",
+    "<|LOC_339|>",
+    "<|LOC_33|>",
+    "<|LOC_340|>",
+    "<|LOC_341|>",
+    "<|LOC_342|>",
+    "<|LOC_343|>",
+    "<|LOC_344|>",
+    "<|LOC_345|>",
+    "<|LOC_346|>",
+    "<|LOC_347|>",
+    "<|LOC_348|>",
+    "<|LOC_349|>",
+    "<|LOC_34|>",
+    "<|LOC_350|>",
+    "<|LOC_351|>",
+    "<|LOC_352|>",
+    "<|LOC_353|>",
+    "<|LOC_354|>",
+    "<|LOC_355|>",
+    "<|LOC_356|>",
+    "<|LOC_357|>",
+    "<|LOC_358|>",
+    "<|LOC_359|>",
+    "<|LOC_35|>",
+    "<|LOC_360|>",
+    "<|LOC_361|>",
+    "<|LOC_362|>",
+    "<|LOC_363|>",
+    "<|LOC_364|>",
+    "<|LOC_365|>",
+    "<|LOC_366|>",
+    "<|LOC_367|>",
+    "<|LOC_368|>",
+    "<|LOC_369|>",
+    "<|LOC_36|>",
+    "<|LOC_370|>",
+    "<|LOC_371|>",
+    "<|LOC_372|>",
+    "<|LOC_373|>",
+    "<|LOC_374|>",
+    "<|LOC_375|>",
+    "<|LOC_376|>",
+    "<|LOC_377|>",
+    "<|LOC_378|>",
+    "<|LOC_379|>",
+    "<|LOC_37|>",
+    "<|LOC_380|>",
+    "<|LOC_381|>",
+    "<|LOC_382|>",
+    "<|LOC_383|>",
+    "<|LOC_384|>",
+    "<|LOC_385|>",
+    "<|LOC_386|>",
+    "<|LOC_387|>",
+    "<|LOC_388|>",
+    "<|LOC_389|>",
+    "<|LOC_38|>",
+    "<|LOC_390|>",
+    "<|LOC_391|>",
+    "<|LOC_392|>",
+    "<|LOC_393|>",
+    "<|LOC_394|>",
+    "<|LOC_395|>",
+    "<|LOC_396|>",
+    "<|LOC_397|>",
+    "<|LOC_398|>",
+    "<|LOC_399|>",
+    "<|LOC_39|>",
+    "<|LOC_3|>",
+    "<|LOC_400|>",
+    "<|LOC_401|>",
+    "<|LOC_402|>",
+    "<|LOC_403|>",
+    "<|LOC_404|>",
+    "<|LOC_405|>",
+    "<|LOC_406|>",
+    "<|LOC_407|>",
+    "<|LOC_408|>",
+    "<|LOC_409|>",
+    "<|LOC_40|>",
+    "<|LOC_410|>",
+    "<|LOC_411|>",
+    "<|LOC_412|>",
+    "<|LOC_413|>",
+    "<|LOC_414|>",
+    "<|LOC_415|>",
+    "<|LOC_416|>",
+    "<|LOC_417|>",
+    "<|LOC_418|>",
+    "<|LOC_419|>",
+    "<|LOC_41|>",
+    "<|LOC_420|>",
+    "<|LOC_421|>",
+    "<|LOC_422|>",
+    "<|LOC_423|>",
+    "<|LOC_424|>",
+    "<|LOC_425|>",
+    "<|LOC_426|>",
+    "<|LOC_427|>",
+    "<|LOC_428|>",
+    "<|LOC_429|>",
+    "<|LOC_42|>",
+    "<|LOC_430|>",
+    "<|LOC_431|>",
+    "<|LOC_432|>",
+    "<|LOC_433|>",
+    "<|LOC_434|>",
+    "<|LOC_435|>",
+    "<|LOC_436|>",
+    "<|LOC_437|>",
+    "<|LOC_438|>",
+    "<|LOC_439|>",
+    "<|LOC_43|>",
+    "<|LOC_440|>",
+    "<|LOC_441|>",
+    "<|LOC_442|>",
+    "<|LOC_443|>",
+    "<|LOC_444|>",
+    "<|LOC_445|>",
+    "<|LOC_446|>",
+    "<|LOC_447|>",
+    "<|LOC_448|>",
+    "<|LOC_449|>",
+    "<|LOC_44|>",
+    "<|LOC_450|>",
+    "<|LOC_451|>",
+    "<|LOC_452|>",
+    "<|LOC_453|>",
+    "<|LOC_454|>",
+    "<|LOC_455|>",
+    "<|LOC_456|>",
+    "<|LOC_457|>",
+    "<|LOC_458|>",
+    "<|LOC_459|>",
+    "<|LOC_45|>",
+    "<|LOC_460|>",
+    "<|LOC_461|>",
+    "<|LOC_462|>",
+    "<|LOC_463|>",
+    "<|LOC_464|>",
+    "<|LOC_465|>",
+    "<|LOC_466|>",
+    "<|LOC_467|>",
+    "<|LOC_468|>",
+    "<|LOC_469|>",
+    "<|LOC_46|>",
+    "<|LOC_470|>",
+    "<|LOC_471|>",
+    "<|LOC_472|>",
+    "<|LOC_473|>",
+    "<|LOC_474|>",
+    "<|LOC_475|>",
+    "<|LOC_476|>",
+    "<|LOC_477|>",
+    "<|LOC_478|>",
+    "<|LOC_479|>",
+    "<|LOC_47|>",
+    "<|LOC_480|>",
+    "<|LOC_481|>",
+    "<|LOC_482|>",
+    "<|LOC_483|>",
+    "<|LOC_484|>",
+    "<|LOC_485|>",
+    "<|LOC_486|>",
+    "<|LOC_487|>",
+    "<|LOC_488|>",
+    "<|LOC_489|>",
+    "<|LOC_48|>",
+    "<|LOC_490|>",
+    "<|LOC_491|>",
+    "<|LOC_492|>",
+    "<|LOC_493|>",
+    "<|LOC_494|>",
+    "<|LOC_495|>",
+    "<|LOC_496|>",
+    "<|LOC_497|>",
+    "<|LOC_498|>",
+    "<|LOC_499|>",
+    "<|LOC_49|>",
+    "<|LOC_4|>",
+    "<|LOC_500|>",
+    "<|LOC_501|>",
+    "<|LOC_502|>",
+    "<|LOC_503|>",
+    "<|LOC_504|>",
+    "<|LOC_505|>",
+    "<|LOC_506|>",
+    "<|LOC_507|>",
+    "<|LOC_508|>",
+    "<|LOC_509|>",
+    "<|LOC_50|>",
+    "<|LOC_510|>",
+    "<|LOC_511|>",
+    "<|LOC_512|>",
+    "<|LOC_513|>",
+    "<|LOC_514|>",
+    "<|LOC_515|>",
+    "<|LOC_516|>",
+    "<|LOC_517|>",
+    "<|LOC_518|>",
+    "<|LOC_519|>",
+    "<|LOC_51|>",
+    "<|LOC_520|>",
+    "<|LOC_521|>",
+    "<|LOC_522|>",
+    "<|LOC_523|>",
+    "<|LOC_524|>",
+    "<|LOC_525|>",
+    "<|LOC_526|>",
+    "<|LOC_527|>",
+    "<|LOC_528|>",
+    "<|LOC_529|>",
+    "<|LOC_52|>",
+    "<|LOC_530|>",
+    "<|LOC_531|>",
+    "<|LOC_532|>",
+    "<|LOC_533|>",
+    "<|LOC_534|>",
+    "<|LOC_535|>",
+    "<|LOC_536|>",
+    "<|LOC_537|>",
+    "<|LOC_538|>",
+    "<|LOC_539|>",
+    "<|LOC_53|>",
+    "<|LOC_540|>",
+    "<|LOC_541|>",
+    "<|LOC_542|>",
+    "<|LOC_543|>",
+    "<|LOC_544|>",
+    "<|LOC_545|>",
+    "<|LOC_546|>",
+    "<|LOC_547|>",
+    "<|LOC_548|>",
+    "<|LOC_549|>",
+    "<|LOC_54|>",
+    "<|LOC_550|>",
+    "<|LOC_551|>",
+    "<|LOC_552|>",
+    "<|LOC_553|>",
+    "<|LOC_554|>",
+    "<|LOC_555|>",
+    "<|LOC_556|>",
+    "<|LOC_557|>",
+    "<|LOC_558|>",
+    "<|LOC_559|>",
+    "<|LOC_55|>",
+    "<|LOC_560|>",
+    "<|LOC_561|>",
+    "<|LOC_562|>",
+    "<|LOC_563|>",
+    "<|LOC_564|>",
+    "<|LOC_565|>",
+    "<|LOC_566|>",
+    "<|LOC_567|>",
+    "<|LOC_568|>",
+    "<|LOC_569|>",
+    "<|LOC_56|>",
+    "<|LOC_570|>",
+    "<|LOC_571|>",
+    "<|LOC_572|>",
+    "<|LOC_573|>",
+    "<|LOC_574|>",
+    "<|LOC_575|>",
+    "<|LOC_576|>",
+    "<|LOC_577|>",
+    "<|LOC_578|>",
+    "<|LOC_579|>",
+    "<|LOC_57|>",
+    "<|LOC_580|>",
+    "<|LOC_581|>",
+    "<|LOC_582|>",
+    "<|LOC_583|>",
+    "<|LOC_584|>",
+    "<|LOC_585|>",
+    "<|LOC_586|>",
+    "<|LOC_587|>",
+    "<|LOC_588|>",
+    "<|LOC_589|>",
+    "<|LOC_58|>",
+    "<|LOC_590|>",
+    "<|LOC_591|>",
+    "<|LOC_592|>",
+    "<|LOC_593|>",
+    "<|LOC_594|>",
+    "<|LOC_595|>",
+    "<|LOC_596|>",
+    "<|LOC_597|>",
+    "<|LOC_598|>",
+    "<|LOC_599|>",
+    "<|LOC_59|>",
+    "<|LOC_5|>",
+    "<|LOC_600|>",
+    "<|LOC_601|>",
+    "<|LOC_602|>",
+    "<|LOC_603|>",
+    "<|LOC_604|>",
+    "<|LOC_605|>",
+    "<|LOC_606|>",
+    "<|LOC_607|>",
+    "<|LOC_608|>",
+    "<|LOC_609|>",
+    "<|LOC_60|>",
+    "<|LOC_610|>",
+    "<|LOC_611|>",
+    "<|LOC_612|>",
+    "<|LOC_613|>",
+    "<|LOC_614|>",
+    "<|LOC_615|>",
+    "<|LOC_616|>",
+    "<|LOC_617|>",
+    "<|LOC_618|>",
+    "<|LOC_619|>",
+    "<|LOC_61|>",
+    "<|LOC_620|>",
+    "<|LOC_621|>",
+    "<|LOC_622|>",
+    "<|LOC_623|>",
+    "<|LOC_624|>",
+    "<|LOC_625|>",
+    "<|LOC_626|>",
+    "<|LOC_627|>",
+    "<|LOC_628|>",
+    "<|LOC_629|>",
+    "<|LOC_62|>",
+    "<|LOC_630|>",
+    "<|LOC_631|>",
+    "<|LOC_632|>",
+    "<|LOC_633|>",
+    "<|LOC_634|>",
+    "<|LOC_635|>",
+    "<|LOC_636|>",
+    "<|LOC_637|>",
+    "<|LOC_638|>",
+    "<|LOC_639|>",
+    "<|LOC_63|>",
+    "<|LOC_640|>",
+    "<|LOC_641|>",
+    "<|LOC_642|>",
+    "<|LOC_643|>",
+    "<|LOC_644|>",
+    "<|LOC_645|>",
+    "<|LOC_646|>",
+    "<|LOC_647|>",
+    "<|LOC_648|>",
+    "<|LOC_649|>",
+    "<|LOC_64|>",
+    "<|LOC_650|>",
+    "<|LOC_651|>",
+    "<|LOC_652|>",
+    "<|LOC_653|>",
+    "<|LOC_654|>",
+    "<|LOC_655|>",
+    "<|LOC_656|>",
+    "<|LOC_657|>",
+    "<|LOC_658|>",
+    "<|LOC_659|>",
+    "<|LOC_65|>",
+    "<|LOC_660|>",
+    "<|LOC_661|>",
+    "<|LOC_662|>",
+    "<|LOC_663|>",
+    "<|LOC_664|>",
+    "<|LOC_665|>",
+    "<|LOC_666|>",
+    "<|LOC_667|>",
+    "<|LOC_668|>",
+    "<|LOC_669|>",
+    "<|LOC_66|>",
+    "<|LOC_670|>",
+    "<|LOC_671|>",
+    "<|LOC_672|>",
+    "<|LOC_673|>",
+    "<|LOC_674|>",
+    "<|LOC_675|>",
+    "<|LOC_676|>",
+    "<|LOC_677|>",
+    "<|LOC_678|>",
+    "<|LOC_679|>",
+    "<|LOC_67|>",
+    "<|LOC_680|>",
+    "<|LOC_681|>",
+    "<|LOC_682|>",
+    "<|LOC_683|>",
+    "<|LOC_684|>",
+    "<|LOC_685|>",
+    "<|LOC_686|>",
+    "<|LOC_687|>",
+    "<|LOC_688|>",
+    "<|LOC_689|>",
+    "<|LOC_68|>",
+    "<|LOC_690|>",
+    "<|LOC_691|>",
+    "<|LOC_692|>",
+    "<|LOC_693|>",
+    "<|LOC_694|>",
+    "<|LOC_695|>",
+    "<|LOC_696|>",
+    "<|LOC_697|>",
+    "<|LOC_698|>",
+    "<|LOC_699|>",
+    "<|LOC_69|>",
+    "<|LOC_6|>",
+    "<|LOC_700|>",
+    "<|LOC_701|>",
+    "<|LOC_702|>",
+    "<|LOC_703|>",
+    "<|LOC_704|>",
+    "<|LOC_705|>",
+    "<|LOC_706|>",
+    "<|LOC_707|>",
+    "<|LOC_708|>",
+    "<|LOC_709|>",
+    "<|LOC_70|>",
+    "<|LOC_710|>",
+    "<|LOC_711|>",
+    "<|LOC_712|>",
+    "<|LOC_713|>",
+    "<|LOC_714|>",
+    "<|LOC_715|>",
+    "<|LOC_716|>",
+    "<|LOC_717|>",
+    "<|LOC_718|>",
+    "<|LOC_719|>",
+    "<|LOC_71|>",
+    "<|LOC_720|>",
+    "<|LOC_721|>",
+    "<|LOC_722|>",
+    "<|LOC_723|>",
+    "<|LOC_724|>",
+    "<|LOC_725|>",
+    "<|LOC_726|>",
+    "<|LOC_727|>",
+    "<|LOC_728|>",
+    "<|LOC_729|>",
+    "<|LOC_72|>",
+    "<|LOC_730|>",
+    "<|LOC_731|>",
+    "<|LOC_732|>",
+    "<|LOC_733|>",
+    "<|LOC_734|>",
+    "<|LOC_735|>",
+    "<|LOC_736|>",
+    "<|LOC_737|>",
+    "<|LOC_738|>",
+    "<|LOC_739|>",
+    "<|LOC_73|>",
+    "<|LOC_740|>",
+    "<|LOC_741|>",
+    "<|LOC_742|>",
+    "<|LOC_743|>",
+    "<|LOC_744|>",
+    "<|LOC_745|>",
+    "<|LOC_746|>",
+    "<|LOC_747|>",
+    "<|LOC_748|>",
+    "<|LOC_749|>",
+    "<|LOC_74|>",
+    "<|LOC_750|>",
+    "<|LOC_751|>",
+    "<|LOC_752|>",
+    "<|LOC_753|>",
+    "<|LOC_754|>",
+    "<|LOC_755|>",
+    "<|LOC_756|>",
+    "<|LOC_757|>",
+    "<|LOC_758|>",
+    "<|LOC_759|>",
+    "<|LOC_75|>",
+    "<|LOC_760|>",
+    "<|LOC_761|>",
+    "<|LOC_762|>",
+    "<|LOC_763|>",
+    "<|LOC_764|>",
+    "<|LOC_765|>",
+    "<|LOC_766|>",
+    "<|LOC_767|>",
+    "<|LOC_768|>",
+    "<|LOC_769|>",
+    "<|LOC_76|>",
+    "<|LOC_770|>",
+    "<|LOC_771|>",
+    "<|LOC_772|>",
+    "<|LOC_773|>",
+    "<|LOC_774|>",
+    "<|LOC_775|>",
+    "<|LOC_776|>",
+    "<|LOC_777|>",
+    "<|LOC_778|>",
+    "<|LOC_779|>",
+    "<|LOC_77|>",
+    "<|LOC_780|>",
+    "<|LOC_781|>",
+    "<|LOC_782|>",
+    "<|LOC_783|>",
+    "<|LOC_784|>",
+    "<|LOC_785|>",
+    "<|LOC_786|>",
+    "<|LOC_787|>",
+    "<|LOC_788|>",
+    "<|LOC_789|>",
+    "<|LOC_78|>",
+    "<|LOC_790|>",
+    "<|LOC_791|>",
+    "<|LOC_792|>",
+    "<|LOC_793|>",
+    "<|LOC_794|>",
+    "<|LOC_795|>",
+    "<|LOC_796|>",
+    "<|LOC_797|>",
+    "<|LOC_798|>",
+    "<|LOC_799|>",
+    "<|LOC_79|>",
+    "<|LOC_7|>",
+    "<|LOC_800|>",
+    "<|LOC_801|>",
+    "<|LOC_802|>",
+    "<|LOC_803|>",
+    "<|LOC_804|>",
+    "<|LOC_805|>",
+    "<|LOC_806|>",
+    "<|LOC_807|>",
+    "<|LOC_808|>",
+    "<|LOC_809|>",
+    "<|LOC_80|>",
+    "<|LOC_810|>",
+    "<|LOC_811|>",
+    "<|LOC_812|>",
+    "<|LOC_813|>",
+    "<|LOC_814|>",
+    "<|LOC_815|>",
+    "<|LOC_816|>",
+    "<|LOC_817|>",
+    "<|LOC_818|>",
+    "<|LOC_819|>",
+    "<|LOC_81|>",
+    "<|LOC_820|>",
+    "<|LOC_821|>",
+    "<|LOC_822|>",
+    "<|LOC_823|>",
+    "<|LOC_824|>",
+    "<|LOC_825|>",
+    "<|LOC_826|>",
+    "<|LOC_827|>",
+    "<|LOC_828|>",
+    "<|LOC_829|>",
+    "<|LOC_82|>",
+    "<|LOC_830|>",
+    "<|LOC_831|>",
+    "<|LOC_832|>",
+    "<|LOC_833|>",
+    "<|LOC_834|>",
+    "<|LOC_835|>",
+    "<|LOC_836|>",
+    "<|LOC_837|>",
+    "<|LOC_838|>",
+    "<|LOC_839|>",
+    "<|LOC_83|>",
+    "<|LOC_840|>",
+    "<|LOC_841|>",
+    "<|LOC_842|>",
+    "<|LOC_843|>",
+    "<|LOC_844|>",
+    "<|LOC_845|>",
+    "<|LOC_846|>",
+    "<|LOC_847|>",
+    "<|LOC_848|>",
+    "<|LOC_849|>",
+    "<|LOC_84|>",
+    "<|LOC_850|>",
+    "<|LOC_851|>",
+    "<|LOC_852|>",
+    "<|LOC_853|>",
+    "<|LOC_854|>",
+    "<|LOC_855|>",
+    "<|LOC_856|>",
+    "<|LOC_857|>",
+    "<|LOC_858|>",
+    "<|LOC_859|>",
+    "<|LOC_85|>",
+    "<|LOC_860|>",
+    "<|LOC_861|>",
+    "<|LOC_862|>",
+    "<|LOC_863|>",
+    "<|LOC_864|>",
+    "<|LOC_865|>",
+    "<|LOC_866|>",
+    "<|LOC_867|>",
+    "<|LOC_868|>",
+    "<|LOC_869|>",
+    "<|LOC_86|>",
+    "<|LOC_870|>",
+    "<|LOC_871|>",
+    "<|LOC_872|>",
+    "<|LOC_873|>",
+    "<|LOC_874|>",
+    "<|LOC_875|>",
+    "<|LOC_876|>",
+    "<|LOC_877|>",
+    "<|LOC_878|>",
+    "<|LOC_879|>",
+    "<|LOC_87|>",
+    "<|LOC_880|>",
+    "<|LOC_881|>",
+    "<|LOC_882|>",
+    "<|LOC_883|>",
+    "<|LOC_884|>",
+    "<|LOC_885|>",
+    "<|LOC_886|>",
+    "<|LOC_887|>",
+    "<|LOC_888|>",
+    "<|LOC_889|>",
+    "<|LOC_88|>",
+    "<|LOC_890|>",
+    "<|LOC_891|>",
+    "<|LOC_892|>",
+    "<|LOC_893|>",
+    "<|LOC_894|>",
+    "<|LOC_895|>",
+    "<|LOC_896|>",
+    "<|LOC_897|>",
+    "<|LOC_898|>",
+    "<|LOC_899|>",
+    "<|LOC_89|>",
+    "<|LOC_8|>",
+    "<|LOC_900|>",
+    "<|LOC_901|>",
+    "<|LOC_902|>",
+    "<|LOC_903|>",
+    "<|LOC_904|>",
+    "<|LOC_905|>",
+    "<|LOC_906|>",
+    "<|LOC_907|>",
+    "<|LOC_908|>",
+    "<|LOC_909|>",
+    "<|LOC_90|>",
+    "<|LOC_910|>",
+    "<|LOC_911|>",
+    "<|LOC_912|>",
+    "<|LOC_913|>",
+    "<|LOC_914|>",
+    "<|LOC_915|>",
+    "<|LOC_916|>",
+    "<|LOC_917|>",
+    "<|LOC_918|>",
+    "<|LOC_919|>",
+    "<|LOC_91|>",
+    "<|LOC_920|>",
+    "<|LOC_921|>",
+    "<|LOC_922|>",
+    "<|LOC_923|>",
+    "<|LOC_924|>",
+    "<|LOC_925|>",
+    "<|LOC_926|>",
+    "<|LOC_927|>",
+    "<|LOC_928|>",
+    "<|LOC_929|>",
+    "<|LOC_92|>",
+    "<|LOC_930|>",
+    "<|LOC_931|>",
+    "<|LOC_932|>",
+    "<|LOC_933|>",
+    "<|LOC_934|>",
+    "<|LOC_935|>",
+    "<|LOC_936|>",
+    "<|LOC_937|>",
+    "<|LOC_938|>",
+    "<|LOC_939|>",
+    "<|LOC_93|>",
+    "<|LOC_940|>",
+    "<|LOC_941|>",
+    "<|LOC_942|>",
+    "<|LOC_943|>",
+    "<|LOC_944|>",
+    "<|LOC_945|>",
+    "<|LOC_946|>",
+    "<|LOC_947|>",
+    "<|LOC_948|>",
+    "<|LOC_949|>",
+    "<|LOC_94|>",
+    "<|LOC_950|>",
+    "<|LOC_951|>",
+    "<|LOC_952|>",
+    "<|LOC_953|>",
+    "<|LOC_954|>",
+    "<|LOC_955|>",
+    "<|LOC_956|>",
+    "<|LOC_957|>",
+    "<|LOC_958|>",
+    "<|LOC_959|>",
+    "<|LOC_95|>",
+    "<|LOC_960|>",
+    "<|LOC_961|>",
+    "<|LOC_962|>",
+    "<|LOC_963|>",
+    "<|LOC_964|>",
+    "<|LOC_965|>",
+    "<|LOC_966|>",
+    "<|LOC_967|>",
+    "<|LOC_968|>",
+    "<|LOC_969|>",
+    "<|LOC_96|>",
+    "<|LOC_970|>",
+    "<|LOC_971|>",
+    "<|LOC_972|>",
+    "<|LOC_973|>",
+    "<|LOC_974|>",
+    "<|LOC_975|>",
+    "<|LOC_976|>",
+    "<|LOC_977|>",
+    "<|LOC_978|>",
+    "<|LOC_979|>",
+    "<|LOC_97|>",
+    "<|LOC_980|>",
+    "<|LOC_981|>",
+    "<|LOC_982|>",
+    "<|LOC_983|>",
+    "<|LOC_984|>",
+    "<|LOC_985|>",
+    "<|LOC_986|>",
+    "<|LOC_987|>",
+    "<|LOC_988|>",
+    "<|LOC_989|>",
+    "<|LOC_98|>",
+    "<|LOC_990|>",
+    "<|LOC_991|>",
+    "<|LOC_992|>",
+    "<|LOC_993|>",
+    "<|LOC_994|>",
+    "<|LOC_995|>",
+    "<|LOC_996|>",
+    "<|LOC_997|>",
+    "<|LOC_998|>",
+    "<|LOC_999|>",
+    "<|LOC_99|>",
+    "<|LOC_9|>",
+    "<|LOC_BEGIN|>",
+    "<|LOC_END|>",
+    "<|LOC_SEP|>",
+    "<|TEXT_END|>",
+    "<|TEXT_START|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask:1>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "processor_class": "PaddleOCRVLProcessor",
+  "sep_token": "<|end_of_sentence|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "image_token": "<|IMAGE_PLACEHOLDER|>"
+}