MLX bfloat16 conversion of naver/v-splade-efficient

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: naver/v-splade-efficient
+tags:
+- mlx
+- v-splade
+- splade
+- visual-document-retrieval
+- sparse-retrieval
+- multimodal
+pipeline_tag: visual-document-retrieval
+---
+
+# v-splade-efficient-mlx
+
+MLX (bfloat16) conversion of [`naver/v-splade-efficient`](https://huggingface.co/naver/v-splade-efficient)
+(V-SPLADE, [arXiv:2605.30917](https://arxiv.org/abs/2605.30917)) for Apple Silicon,
+produced by [NomaDamas/SPLADE-mlx](https://github.com/NomaDamas/SPLADE-mlx).
+
+V-SPLADE is an inference-free sparse retriever for visual document retrieval:
+document pages (rendered PDFs, slides, scans) are encoded by a ModernVBERT
+backbone (SigLIP vision tower + pixel-shuffle connector + ModernBERT text
+encoder) with a SPLADE MLM head into a 50,368-dim vocabulary-space sparse
+vector, while queries are resolved by a learned Bag-of-Words lookup with no
+neural encoding at all.
+
+**Contents**: `weights.safetensors` (document encoder, bfloat16),
+`query_lookup.npy` (inference-free query table, fp32), `config.json`,
+plus tokenizer/processor configs for self-contained loading.
+
+**Changes from upstream**: PyTorch checkpoint converted to MLX safetensors
+(parameter re-mapping, conv weight transposed to NHWC, cast to bfloat16); the
+query lookup table `softplus(embedding @ projection + bias)` is precomputed
+with special tokens zeroed. No training or fine-tuning was performed.
+
+**Quality** (see repo REPORT.md for methodology):
+- fp32 parity vs the PyTorch reference: max |logit delta| 1.5e-04 on
+  real document-page inputs, sparse-vector cosine 1.000000, top-64 term
+  overlap 100%; the query table matches the shipped Sentence Transformers
+  static embedding to 1.2e-07.
+- ViDoRe `docvqa_test_subsampled` nDCG@5 (fp32): 0.4098 (torch) ->
+  0.4098 (MLX), delta +0.0000 (gate: ±0.002).
+
+## Usage
+
+```python
+from splade_mlx.convert_vsplade import load_vsplade
+import mlx.core as mx
+from PIL import Image
+
+model, query_encoder, processor = load_vsplade("NomaDamas/v-splade-efficient-mlx")
+
+# documents (page images)
+enc = processor(text=["User:<image><end_of_utterance>\nAssistant:"],
+                images=[[Image.open("page.png")]], return_tensors="np")
+d = model.encode(mx.array(enc["input_ids"]), mx.array(enc["attention_mask"]),
+                 enc["pixel_values"])   # (1, 50368)
+
+# queries: inference-free lookup, no neural network
+q = processor.tokenizer(["total revenue 2023"], return_tensors="np")
+qw = query_encoder.encode(q["input_ids"], q["attention_mask"])  # (1, 50368)
+
+score = d @ qw.T
+```
+
+## License
+
+Apache-2.0, same as the upstream checkpoint (© NAVER Corp).
+This repository is not affiliated with or endorsed by NAVER.

chat_template.jinja

@@ -0,0 +1,2 @@
+{% 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 %}{% if add_generation_prompt %}<end_of_utterance>
+{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}

config.json

@@ -0,0 +1,110 @@
+{
+  "auto_map": {
+    "AutoModelForMaskedLM": "modeling_vsplade.VSPLADEForMaskedLM"
+  },
+  "image_token_id": 50407,
+  "initializer_range": 0.02,
+  "model_type": "modernvbert",
+  "pixel_shuffle_factor": 4,
+  "text_config": {
+    "_name_or_path": "ettin-encoder-150m",
+    "architectures": [
+      "ModernBertForMaskedLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "causal_mask": false,
+    "classifier_activation": "gelu",
+    "classifier_bias": false,
+    "classifier_dropout": 0.0,
+    "classifier_pooling": "mean",
+    "cls_token_id": 50281,
+    "decoder_bias": true,
+    "deterministic_flash_attn": false,
+    "dtype": "float32",
+    "embedding_dropout": 0.0,
+    "global_attn_every_n_layers": 3,
+    "global_rope_theta": 160000.0,
+    "gradient_checkpointing": false,
+    "hidden_activation": "gelu",
+    "hidden_size": 768,
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1152,
+    "is_causal": false,
+    "layer_norm_eps": 1e-05,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "local_attention": 128,
+    "local_rope_theta": 160000.0,
+    "max_position_embeddings": 7999,
+    "mlp_bias": false,
+    "mlp_dropout": 0.0,
+    "model_type": "modernbert",
+    "norm_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 22,
+    "position_embedding_type": "sans_pos",
+    "repad_logits_with_grad": false,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      }
+    },
+    "sparse_pred_ignore_index": -100,
+    "sparse_prediction": false,
+    "vocab_size": 50408
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 512,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16
+  },
+  "tie_word_embeddings": false,
+  "architectures": [
+    "BiModernVBert"
+  ],
+  "freeze_config": {
+    "freeze_lm_head": true,
+    "freeze_text_layers": true,
+    "freeze_vision_layers": true
+  },
+  "additional_vocab_size": 40
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98267e6f8b102a88667dec368ae8247d9d0fd7c60a5ce59053474331f72a84ff
+size 660070138

modeling_vsplade.py

@@ -0,0 +1,175 @@
+"""V-SPLADE document encoder for Hugging Face Transformers.
+
+Wraps the ModernVBERT backbone (``transformers>=5.3.0``) together with the
+V-SPLADE MLM head so that this repository loads directly with
+``AutoModelForMaskedLM.from_pretrained(..., trust_remote_code=True)``.
+
+The module tree deliberately mirrors the checkpoint layout of the V-SPLADE
+export (``encoder.encoder.model.*`` for the backbone, ``encoder.mlm_head.*``
+for the sparse head), so ``model.safetensors`` loads without any key
+remapping. The ``query_encoder.*`` tensors hold the inference-free Li-LSR
+query lookup (used by the Sentence Transformers integration) and are not part
+of the document encoder, so they are ignored here.
+
+The returned ``logits`` are the SPLADE term logits: MLM logits scaled by
+``hidden_size ** -0.25`` with special tokens masked out, exactly as in
+https://github.com/naver/v-splade (``UnifiedRetriever._apply_sparse_head``).
+A sparse document embedding is obtained via ``log1p(relu(logits))`` followed
+by a max-pool over the sequence dimension (see the README).
+"""
+
+from __future__ import annotations
+
+import torch
+import torch.nn.functional as F
+from torch import nn
+from transformers.modeling_outputs import MaskedLMOutput
+
+try:
+    from transformers.models.modernvbert.configuration_modernvbert import ModernVBertConfig
+    from transformers.models.modernvbert.modeling_modernvbert import (
+        ModernVBertModel,
+        ModernVBertPreTrainedModel,
+    )
+except ImportError as exc:
+    raise ImportError(
+        "V-SPLADE requires the ModernVBERT architecture, which is available in "
+        "transformers>=5.3.0. Please upgrade with `pip install -U transformers`."
+    ) from exc
+
+# Special tokens that are masked out of the sparse representation:
+# [UNK], [CLS], [SEP], [PAD], [MASK]
+SPECIAL_TOKEN_IDS = [50280, 50281, 50282, 50283, 50284]
+
+
+class VSPLADEDecoupledEmbedding(nn.Embedding):
+    """Word embeddings split into the base vocabulary and the added vision tokens.
+
+    Matches the V-SPLADE export layout: ``weight`` holds the base (MLM) vocabulary
+    and ``additional_embedding.weight`` holds the extra tokens appended for the
+    vision chat format (``<image>``, ``<end_of_utterance>``, tile markers, ...).
+    """
+
+    def __init__(self, num_embeddings: int, num_additional_embeddings: int, embedding_dim: int, **kwargs) -> None:
+        super().__init__(num_embeddings, embedding_dim, **kwargs)
+        self.num_additional_embeddings = num_additional_embeddings
+        self.additional_embedding = nn.Embedding(num_additional_embeddings, embedding_dim)
+
+    def forward(self, input_ids: torch.LongTensor) -> torch.Tensor:
+        input_ids = input_ids.clone()
+        additional_vocab_indices = torch.where(input_ids >= self.num_embeddings)
+        additional_embeddings = self.additional_embedding(input_ids[additional_vocab_indices] - self.num_embeddings)
+        input_ids[additional_vocab_indices] = 0
+        full_vector = F.embedding(input_ids, self.weight)
+        full_vector[additional_vocab_indices] = additional_embeddings
+        return full_vector
+
+
+class VSPLADEModalityProjection(nn.Module):
+    """Vision-to-text projection stored as ``modality_projection.proj`` in the export."""
+
+    def __init__(self, input_size: int, output_size: int) -> None:
+        super().__init__()
+        self.proj = nn.Linear(input_size, output_size, bias=False)
+
+    @property
+    def weight(self) -> torch.Tensor:
+        # ModernVBertPreTrainedModel._init_weights initializes ``modality_projection.weight``
+        return self.proj.weight
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        return self.proj(hidden_states)
+
+
+class VSPLADEMLMHead(nn.Module):
+    """V-SPLADE MLM head: dense -> GELU -> LayerNorm -> decoder (base vocabulary)."""
+
+    def __init__(self, hidden_size: int, vocab_size: int) -> None:
+        super().__init__()
+        self.dense = nn.Linear(hidden_size, hidden_size)
+        self.norm = nn.LayerNorm(hidden_size)
+        self.decoder = nn.Linear(hidden_size, vocab_size)
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        return self.decoder(self.norm(F.gelu(self.dense(hidden_states))))
+
+
+class _Wrapper(nn.Module):
+    """Empty container used to mirror the checkpoint's key prefixes."""
+
+
+class VSPLADEForMaskedLM(ModernVBertPreTrainedModel):
+    config_class = ModernVBertConfig
+    _keys_to_ignore_on_load_unexpected = [r"query_encoder\..*"]
+
+    def __init__(self, config: ModernVBertConfig) -> None:
+        super().__init__(config)
+        main_vocab_size = config.text_config.vocab_size - config.additional_vocab_size
+
+        backbone = ModernVBertModel(config)
+        # The export stores the connector projection under an extra ``proj`` level; mirror that.
+        backbone.connector.modality_projection = VSPLADEModalityProjection(
+            input_size=config.vision_config.hidden_size * (config.pixel_shuffle_factor**2),
+            output_size=config.text_config.hidden_size,
+        )
+        # The export splits the embedding into base + additional tokens; mirror that.
+        backbone.text_model.set_input_embeddings(
+            VSPLADEDecoupledEmbedding(
+                num_embeddings=main_vocab_size,
+                num_additional_embeddings=config.additional_vocab_size,
+                embedding_dim=config.text_config.hidden_size,
+                padding_idx=getattr(config, "pad_token_id", None),
+            )
+        )
+
+        self.encoder = _Wrapper()
+        self.encoder.encoder = _Wrapper()
+        self.encoder.encoder.model = backbone
+        self.encoder.mlm_head = VSPLADEMLMHead(config.text_config.hidden_size, main_vocab_size)
+
+        self.logit_scale = config.text_config.hidden_size**-0.25
+
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.encoder.encoder.model.get_input_embeddings()
+
+    def set_input_embeddings(self, value):
+        self.encoder.encoder.model.set_input_embeddings(value)
+
+    def forward(
+        self,
+        input_ids: torch.LongTensor | None = None,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        inputs_embeds: torch.FloatTensor | None = None,
+        pixel_values: torch.FloatTensor | None = None,
+        pixel_attention_mask: torch.BoolTensor | None = None,
+        image_hidden_states: torch.FloatTensor | None = None,
+        return_dict: bool | None = None,
+    ) -> MaskedLMOutput:
+        outputs = self.encoder.encoder.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            inputs_embeds=inputs_embeds,
+            pixel_values=pixel_values,
+            pixel_attention_mask=pixel_attention_mask,
+            image_hidden_states=image_hidden_states,
+            return_dict=True,
+        )
+        logits = self.encoder.mlm_head(outputs.last_hidden_state) * self.logit_scale
+        # Zero out special tokens so they never activate in the sparse representation
+        # (log1p(relu(0)) == 0), matching the reference special_token_mask.
+        # Built on the fly: buffers created in __init__ do not survive meta-device loading.
+        special_token_ids = torch.tensor(SPECIAL_TOKEN_IDS, dtype=torch.long, device=logits.device)
+        logits = logits.index_fill(-1, special_token_ids, 0.0)
+
+        return MaskedLMOutput(
+            logits=logits,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )
+
+
+__all__ = ["VSPLADEForMaskedLM"]

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+    "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
+    },
+    "processor_class": "Idefics3Processor",
+    "resample": 1,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+        "longest_edge": 2048
+    }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+    "image_seq_len": 64,
+    "processor_class": "Idefics3Processor"
+}

query_lookup.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c9cf8d991cd10ce237fa177213cd36209135a52f26c2dc5ed5d347342d9b1c
+size 201600

special_tokens_map.json

@@ -0,0 +1,79 @@
+{
+  "additional_special_tokens": [
+    "<global-img>",
+    "<row_1_col_1>",
+    "<row_1_col_2>",
+    "<row_1_col_3>",
+    "<row_1_col_4>",
+    "<row_1_col_5>",
+    "<row_1_col_6>",
+    "<row_2_col_1>",
+    "<row_2_col_2>",
+    "<row_2_col_3>",
+    "<row_2_col_4>",
+    "<row_2_col_5>",
+    "<row_2_col_6>",
+    "<row_3_col_1>",
+    "<row_3_col_2>",
+    "<row_3_col_3>",
+    "<row_3_col_4>",
+    "<row_3_col_5>",
+    "<row_3_col_6>",
+    "<row_4_col_1>",
+    "<row_4_col_2>",
+    "<row_4_col_3>",
+    "<row_4_col_4>",
+    "<row_4_col_5>",
+    "<row_4_col_6>",
+    "<row_5_col_1>",
+    "<row_5_col_2>",
+    "<row_5_col_3>",
+    "<row_5_col_4>",
+    "<row_5_col_5>",
+    "<row_5_col_6>",
+    "<row_6_col_1>",
+    "<row_6_col_2>",
+    "<row_6_col_3>",
+    "<row_6_col_4>",
+    "<row_6_col_5>",
+    "<row_6_col_6>",
+    "<end_of_utterance>",
+    "<fake_token_around_image>",
+    "<image>"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,1310 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50368": {
+      "content": "<global-img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50369": {
+      "content": "<row_1_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50370": {
+      "content": "<row_1_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50371": {
+      "content": "<row_1_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50372": {
+      "content": "<row_1_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50373": {
+      "content": "<row_1_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50374": {
+      "content": "<row_1_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50375": {
+      "content": "<row_2_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50376": {
+      "content": "<row_2_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50377": {
+      "content": "<row_2_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50378": {
+      "content": "<row_2_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50379": {
+      "content": "<row_2_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50380": {
+      "content": "<row_2_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50381": {
+      "content": "<row_3_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50382": {
+      "content": "<row_3_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50383": {
+      "content": "<row_3_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50384": {
+      "content": "<row_3_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50385": {
+      "content": "<row_3_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50386": {
+      "content": "<row_3_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50387": {
+      "content": "<row_4_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50388": {
+      "content": "<row_4_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50389": {
+      "content": "<row_4_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50390": {
+      "content": "<row_4_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50391": {
+      "content": "<row_4_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50392": {
+      "content": "<row_4_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50393": {
+      "content": "<row_5_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50394": {
+      "content": "<row_5_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50395": {
+      "content": "<row_5_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50396": {
+      "content": "<row_5_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50397": {
+      "content": "<row_5_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50398": {
+      "content": "<row_5_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50399": {
+      "content": "<row_6_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50400": {
+      "content": "<row_6_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50401": {
+      "content": "<row_6_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50402": {
+      "content": "<row_6_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50403": {
+      "content": "<row_6_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50404": {
+      "content": "<row_6_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50405": {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50406": {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50407": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<global-img>",
+    "<row_1_col_1>",
+    "<row_1_col_2>",
+    "<row_1_col_3>",
+    "<row_1_col_4>",
+    "<row_1_col_5>",
+    "<row_1_col_6>",
+    "<row_2_col_1>",
+    "<row_2_col_2>",
+    "<row_2_col_3>",
+    "<row_2_col_4>",
+    "<row_2_col_5>",
+    "<row_2_col_6>",
+    "<row_3_col_1>",
+    "<row_3_col_2>",
+    "<row_3_col_3>",
+    "<row_3_col_4>",
+    "<row_3_col_5>",
+    "<row_3_col_6>",
+    "<row_4_col_1>",
+    "<row_4_col_2>",
+    "<row_4_col_3>",
+    "<row_4_col_4>",
+    "<row_4_col_5>",
+    "<row_4_col_6>",
+    "<row_5_col_1>",
+    "<row_5_col_2>",
+    "<row_5_col_3>",
+    "<row_5_col_4>",
+    "<row_5_col_5>",
+    "<row_5_col_6>",
+    "<row_6_col_1>",
+    "<row_6_col_2>",
+    "<row_6_col_3>",
+    "<row_6_col_4>",
+    "<row_6_col_5>",
+    "<row_6_col_6>",
+    "<end_of_utterance>",
+    "<fake_token_around_image>",
+    "<image>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask",
+    "pixel_values",
+    "pixel_attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec7326002bbf7e3bd992e8dd507b118b7aa86a4ba4f5deb2bf127fc165c9e4d
+size 568518398