Upload folder using huggingface_hub

.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

README.md

@@ -1,202 +1,859 @@
 ---
-base_model: google/paligemma-3b-pt-448
-library_name: peft
+library_name: transformers
+license: gemma
+pipeline_tag: image-text-to-text
+extra_gated_heading: Access PaliGemma on Hugging Face
+extra_gated_prompt: To access PaliGemma on Hugging Face, you’re required to review
+  and agree to Google’s usage license. To do this, please ensure you’re logged-in
+  to Hugging Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
 ---
+# PaliGemma model card
 
-# Model Card for Model ID
+**Model page:** [PaliGemma](https://ai.google.dev/gemma/docs/paligemma)
 
-<!-- Provide a quick summary of what the model is/does. -->
+Transformers PaliGemma 3B weights, pre-trained with 448*448 input images and 512 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
 
+**Resources and technical documentation:**
 
+*   [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
+*   [PaliGemma on Kaggle](https://www.kaggle.com/models/google/paligemma)
+*   [PaliGemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/363)
 
-## Model Details
+**Terms of Use:** [Terms](https://www.kaggle.com/models/google/paligemma/license/consent/verify/huggingface?returnModelRepoId=google/paligemma-3b-pt-448)
 
-### Model Description
+**Authors:** Google
 
-<!-- Provide a longer summary of what this model is. -->
+## Model information
 
+### Model summary
 
+#### Description
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+PaliGemma is a versatile and lightweight vision-language model (VLM) inspired by
+[PaLI-3](https://arxiv.org/abs/2310.09199) and based on open components such as
+the [SigLIP vision model](https://arxiv.org/abs/2303.15343) and the [Gemma
+language model](https://arxiv.org/abs/2403.08295). It takes both image and text
+as input and generates text as output, supporting multiple languages. It is designed for class-leading fine-tune performance on a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation.
 
-### Model Sources [optional]
+#### Model architecture
 
-<!-- Provide the basic links for the model. -->
+PaliGemma is the composition of a [Transformer
+decoder](https://arxiv.org/abs/1706.03762) and a [Vision Transformer image
+encoder](https://arxiv.org/abs/2010.11929), with a total of 3 billion
+params. The text decoder is initialized from
+[Gemma-2B](https://www.kaggle.com/models/google/gemma). The image encoder is
+initialized from
+[SigLIP-So400m/14](https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/SigLIP_demo.ipynb).
+PaliGemma is trained following the PaLI-3 recipes.
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+#### Inputs and outputs
 
-## Uses
+*   **Input:** Image and text string, such as a prompt to caption the image, or
+    a question.
+*   **Output:** Generated text in response to the input, such as a caption of
+    the image, an answer to a question, a list of object bounding box
+    coordinates, or segmentation codewords.
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Model data
 
-### Direct Use
+#### Pre-train datasets
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+PaliGemma is pre-trained on the following mixture of datasets:
 
-[More Information Needed]
+*   **WebLI:** [WebLI (Web Language Image)](https://arxiv.org/abs/2209.06794) is
+    a web-scale multilingual image-text dataset built from the public web. A
+    wide range of WebLI splits are used to acquire versatile model capabilities,
+    such as visual semantic understanding, object localization,
+    visually-situated text understanding, multilinguality, etc.
+*   **CC3M-35L:** Curated English image-alt_text pairs from webpages ([Sharma et
+    al., 2018](https://aclanthology.org/P18-1238/)). We used the [Google Cloud
+    Translation API](https://cloud.google.com/translate) to translate into 34
+    additional languages.
+*   **VQ²A-CC3M-35L/VQG-CC3M-35L:** A subset of VQ2A-CC3M ([Changpinyo et al.,
+    2022a](https://aclanthology.org/2022.naacl-main.142/)), translated into the
+    same additional 34 languages as CC3M-35L, using the [Google Cloud
+    Translation API](https://cloud.google.com/translate).
+*   **OpenImages:** Detection and object-aware questions and answers
+    ([Piergiovanni et al. 2022](https://arxiv.org/abs/2209.04372)) generated by
+    handcrafted rules on the [OpenImages dataset].
+*   **WIT:** Images and texts collected from Wikipedia ([Srinivasan et al.,
+    2021](https://arxiv.org/abs/2103.01913)).
 
-### Downstream Use [optional]
+[OpenImages dataset]: https://storage.googleapis.com/openimages/web/factsfigures_v7.html
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+#### Data responsibility filtering
 
-[More Information Needed]
+The following filters are applied to WebLI, with the goal of training PaliGemma
+on clean data:
 
-### Out-of-Scope Use
+*   **Pornographic image filtering:** This filter removes images deemed to be of
+    pornographic nature.
+*   **Text safety filtering:** We identify and filter out images that are paired
+    with unsafe text. Unsafe text is any text deemed to contain or be about
+    CSAI, pornography, vulgarities, or otherwise offensive.
+*   **Text toxicity filtering:** We further use the [Perspective
+    API](https://perspectiveapi.com/) to identify and filter out images that are
+    paired with text deemed insulting, obscene, hateful or otherwise toxic.
+*   **Text personal information filtering:** We filtered certain personal information and other sensitive data using [Cloud Data Loss Prevention (DLP)
+    API](https://cloud.google.com/security/products/dlp) to protect the privacy
+    of individuals. Identifiers such as social security numbers and [other sensitive information types] were removed.
+*   **Additional methods:** Filtering based on content quality and safety in
+    line with our policies and practices.
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+[other sensitive information types]: https://cloud.google.com/sensitive-data-protection/docs/high-sensitivity-infotypes-reference?_gl=1*jg604m*_ga*ODk5MzA3ODQyLjE3MTAzMzQ3NTk.*_ga_WH2QY8WWF5*MTcxMDUxNTkxMS4yLjEuMTcxMDUxNjA2NC4wLjAuMA..&_ga=2.172110058.-899307842.1710334759
 
-[More Information Needed]
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## How to Use
 
-[More Information Needed]
+PaliGemma is a single-turn vision language model not meant for conversational use,
+and it works best when fine-tuning to a specific use case. 
 
-### Recommendations
+You can configure which task the model will solve by conditioning it with task prefixes,
+such as “detect” or “segment”. The pretrained models were trained in this fashion to imbue
+them with a rich set of capabilities (question answering, captioning, segmentation, etc.).
+However, they are not designed to be used directly, but to be transferred (by fine-tuning)
+to specific tasks using a similar prompt structure. For interactive testing, you can use
+the "mix" family of models, which have been fine-tuned on a mixture of tasks. To see model 
+[google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) in action,
+check [this Space that uses the Transformers codebase](https://huggingface.co/spaces/big-vision/paligemma-hf).
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+Please, refer to the [usage and limitations section](#usage-and-limitations) for intended
+use cases, or visit the [blog post](https://huggingface.co/blog/paligemma-google-vlm) for
+additional details and examples.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+## Use in Transformers
+
+The following snippets use model `google/paligemma-3b-mix-224` for reference purposes.
+The model in this repo you are now browsing may have been trained for other tasks, please
+make sure you use appropriate inputs for the task at hand.
+
+### Running the default precision (`float32`) on CPU
+
+```python
+from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
+from PIL import Image
+import requests
+import torch
+
+model_id = "google/paligemma-3b-mix-224"
+
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
+
+model = PaliGemmaForConditionalGeneration.from_pretrained(model_id).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Instruct the model to create a caption in Spanish
+prompt = "caption es"
+model_inputs = processor(text=prompt, images=image, return_tensors="pt")
+input_len = model_inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+    decoded = processor.decode(generation, skip_special_tokens=True)
+    print(decoded)
+```
 
-## How to Get Started with the Model
+Output: `Un auto azul estacionado frente a un edificio.`
+
+### Running other precisions on CUDA
+
+For convenience, the repos contain revisions of the weights already converted to `bfloat16` and `float16`,
+so you can use them to reduce the download size and avoid casting on your local computer.
 
-Use the code below to get started with the model.
+This is how you'd run `bfloat16` on an nvidia CUDA card.
 
-[More Information Needed]
+```python
+from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
+from PIL import Image
+import requests
+import torch
 
-## Training Details
+model_id = "google/paligemma-3b-mix-224"
+device = "cuda:0"
+dtype = torch.bfloat16
 
-### Training Data
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.12.0
+model = PaliGemmaForConditionalGeneration.from_pretrained(
+    model_id,
+    torch_dtype=dtype,
+    device_map=device,
+    revision="bfloat16",
+).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Instruct the model to create a caption in Spanish
+prompt = "caption es"
+model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+input_len = model_inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+    decoded = processor.decode(generation, skip_special_tokens=True)
+    print(decoded)
+```
+
+### Loading in 4-bit / 8-bit
+
+You need to install `bitsandbytes` to automatically run inference using 8-bit or 4-bit precision:
+
+```
+pip install bitsandbytes accelerate
+```
+
+```
+from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
+from PIL import Image
+import requests
+import torch
+
+model_id = "google/paligemma-3b-mix-224"
+device = "cuda:0"
+dtype = torch.bfloat16
+
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
+
+quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+
+model = PaliGemmaForConditionalGeneration.from_pretrained(
+    model_id, quantization_config=quantization_config
+).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+# Instruct the model to create a caption in Spanish
+prompt = "caption es"
+model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+input_len = model_inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+    decoded = processor.decode(generation, skip_special_tokens=True)
+    print(decoded)
+```
+
+## Implementation information
+
+### Hardware
+
+PaliGemma was trained using the latest generation of Tensor Processing Unit
+(TPU) hardware (TPUv5e).
+
+### Software
+
+Training was done using [JAX](https://github.com/google/jax),
+[Flax](https://github.com/google/flax),
+[TFDS](https://github.com/tensorflow/datasets) and
+[`big_vision`](https://github.com/google-research/big_vision).
+
+JAX allows researchers to take advantage of the latest generation of hardware,
+including TPUs, for faster and more efficient training of large models.
+
+TFDS is used to access datasets and Flax is used for model architecture. The
+PaliGemma fine-tune code and inference code are released in the `big_vision`
+GitHub repository.
+
+## Evaluation information
+
+### Benchmark results
+
+In order to verify the transferability of PaliGemma to a wide variety of
+academic tasks, we fine-tune the pretrained models on each task. Additionally we
+train the mix model with a mixture of the transfer tasks. We report results on
+different resolutions to provide an impression of which tasks benefit from
+increased resolution. Importantly, none of these tasks or datasets are part of
+the pretraining data mixture, and their images are explicitly removed from the
+web-scale pre-training data.
+
+#### Single task (fine-tune on single task)
+
+<table>
+  <tbody><tr>
+    <th>Benchmark<br>(train split)</th>
+    <th>Metric<br>(split)</th>
+    <th>pt-224</th>
+    <th>pt-448</th>
+    <th>pt-896</th>
+  </tr>
+  <tr>
+    <th>Captioning</th>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://cocodataset.org/#home">COCO captions</a><br>(train+restval)
+    </td>
+    <td>CIDEr (val)</td>
+    <td>141.92</td>
+    <td>144.60</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://nocaps.org/">NoCaps</a><br>(Eval of COCO<br>captions transfer)
+    </td>
+    <td>CIDEr (val)</td>
+    <td>121.72</td>
+    <td>123.58</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/pdf/2205.12522">COCO-35L</a><br>(train)
+    </td>
+    <td>CIDEr dev<br>(en/avg-34/avg)</td>
+    <td>
+      139.2<br>
+      115.8<br>
+      116.4
+    </td>
+    <td>
+      141.2<br>
+      118.0<br>
+      118.6
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/pdf/2205.12522">XM3600</a><br>(Eval of COCO-35L transfer)
+    </td>
+    <td>CIDEr dev<br>(en/avg-34/avg)</td>
+    <td>
+      78.1<br>
+      41.3<br>
+      42.4
+    </td>
+    <td>
+      80.0<br>
+      41.9<br>
+      42.9
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://textvqa.org/textcaps/">TextCaps</a><br>(train)
+    </td>
+    <td>CIDEr (val)</td>
+    <td>127.48</td>
+    <td>153.94</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2110.11624">SciCap</a><br>(first sentence, no subfigure)<br>(train+val)
+    </td>
+    <td>CIDEr/BLEU-4<br>(test)</td>
+    <td>
+      162.25<br>
+      0.192<br>
+    </td>
+    <td>
+      181.49<br>
+      0.211<br>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2108.03353">Screen2words</a><br>(train+dev)
+    </td>
+    <td>CIDEr (test)</td>
+    <td>117.57</td>
+    <td>119.59</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2010.04295">Widget Captioning</a><br>(train+dev)
+    </td>
+    <td>CIDEr (test)</td>
+    <td>136.07</td>
+    <td>148.36</td>
+  </tr>
+  <tr>
+    <th>Question answering</th>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://visualqa.org/index.html">VQAv2</a><br>(train+validation)
+    </td>
+    <td>Accuracy<br>(Test server - std)</td>
+    <td>83.19</td>
+    <td>85.64</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2401.06209">MMVP</a><br>(Eval of VQAv2 transfer)
+    </td>
+    <td>Paired Accuracy</td>
+    <td>47.33</td>
+    <td>45.33</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2305.10355">POPE</a><br>(Eval of VQAv2 transfer)
+    </td>
+    <td>Accuracy<br>(random/popular/<br>adversarial)</td>
+    <td>
+      87.80<br>
+      85.87<br>
+      84.27
+    </td>
+    <td>
+      88.23<br>
+      86.77<br>
+      85.90
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://okvqa.allenai.org/">OKVQA</a><br>(train)
+    </td>
+    <td>Accuracy (val)</td>
+    <td>63.54</td>
+    <td>63.15</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (MC)<br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server)</td>
+    <td>76.37</td>
+    <td>76.90</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://allenai.org/project/a-okvqa/home">A-OKVQA</a> (DA)<br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server)</td>
+    <td>61.85</td>
+    <td>63.22</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://cs.stanford.edu/people/dorarad/gqa/about.html">GQA</a><br>(train_balanced+<br>val_balanced)
+    </td>
+    <td>Accuracy<br>(testdev balanced)</td>
+    <td>65.61</td>
+    <td>67.03</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://aclanthology.org/2022.findings-acl.196/">xGQA</a><br>(Eval of GQA transfer)
+    </td>
+    <td>Mean Accuracy<br>(bn, de, en, id,<br>ko, pt, ru, zh)</td>
+    <td>58.37</td>
+    <td>59.07</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://lil.nlp.cornell.edu/nlvr/">NLVR2</a><br>(train+dev)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>90.02</td>
+    <td>88.93</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://marvl-challenge.github.io/">MaRVL</a><br>(Eval of NLVR2 transfer)
+    </td>
+    <td>Mean Accuracy<br>(test)<br>(id, sw, ta, tr, zh)</td>
+    <td>80.57</td>
+    <td>76.78</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://allenai.org/data/diagrams">AI2D</a><br>(train)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>72.12</td>
+    <td>73.28</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://scienceqa.github.io/">ScienceQA</a><br>(Img subset, no CoT)<br>(train+val)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>95.39</td>
+    <td>95.93</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://zenodo.org/records/6344334">RSVQA-LR</a> (Non numeric)<br>(train+val)
+    </td>
+    <td>Mean Accuracy<br>(test)</td>
+    <td>92.65</td>
+    <td>93.11</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://zenodo.org/records/6344367">RSVQA-HR</a> (Non numeric)<br>(train+val)
+    </td>
+    <td>Mean Accuracy<br>(test/test2)</td>
+    <td>
+      92.61<br>
+      90.58
+    </td>
+    <td>
+      92.79<br>
+      90.54
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/2203.10244">ChartQA</a><br>(human+aug)x(train+val)
+    </td>
+    <td>Mean Relaxed<br>Accuracy<br>(test_human,<br>test_aug)</td>
+    <td>57.08</td>
+    <td>71.36</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://vizwiz.org/tasks-and-datasets/vqa/">VizWiz VQA</a><br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server - std)</td>
+    <td>
+      73.7
+    </td>
+    <td>
+      75.52
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/1810.12440">TallyQA</a><br>(train)
+    </td>
+    <td>Accuracy<br>(test_simple/<br>test_complex)</td>
+    <td>
+      81.72<br>
+      69.56
+    </td>
+    <td>
+      84.86<br>
+      72.27
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://ocr-vqa.github.io/">OCR-VQA</a><br>(train+val)
+    </td>
+    <td>Accuracy (test)</td>
+    <td>72.32</td>
+    <td>74.61</td>
+    <td>74.93</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://textvqa.org/">TextVQA</a><br>(train+val)
+    </td>
+    <td>Accuracy<br>(Test server - std)</td>
+    <td>55.47</td>
+    <td>73.15</td>
+    <td>76.48</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://www.docvqa.org/">DocVQA</a><br>(train+val)
+    </td>
+    <td>ANLS (Test server)</td>
+    <td>43.74</td>
+    <td>78.02</td>
+    <td>84.77</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://openaccess.thecvf.com/content/WACV2022/papers/Mathew_InfographicVQA_WACV_2022_paper.pdf">Infographic VQA</a><br>(train+val)
+    </td>
+    <td>ANLS (Test server)</td>
+    <td>28.46</td>
+    <td>40.47</td>
+    <td>47.75</td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/1905.13648">SceneText VQA</a><br>(train+val)
+    </td>
+    <td>ANLS (Test server)</td>
+    <td>63.29</td>
+    <td>81.82</td>
+    <td>84.40</td>
+  </tr>
+  <tr>
+    <th>Segmentation</th>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://arxiv.org/abs/1608.00272">RefCOCO</a><br>(combined refcoco, refcoco+,<br>refcocog excluding val<br>and test images)
+    </td>
+    <td>MIoU<br>(validation)<br>refcoco/refcoco+/<br>refcocog</td>
+    <td>
+      73.40<br>
+      68.32<br>
+      67.65
+    </td>
+    <td>
+      75.57<br>
+      69.76<br>
+      70.17
+    </td>
+    <td>
+      76.94<br>
+      72.18<br>
+      72.22
+    </td>
+  </tr>
+  <tr>
+    <th>Video tasks (Caption/QA)</th>
+  </tr>
+  <tr>
+    <td>MSR-VTT (Captioning)</td>
+    <td>CIDEr (test)</td>
+    <td>70.54</td>
+  </tr>
+  <tr>
+    <td>MSR-VTT (QA)</td>
+    <td>Accuracy (test)</td>
+    <td>50.09</td>
+  </tr>
+  <tr>
+    <td>ActivityNet (Captioning)</td>
+    <td>CIDEr (test)</td>
+    <td>34.62</td>
+  </tr>
+  <tr>
+    <td>ActivityNet (QA)</td>
+    <td>Accuracy (test)</td>
+    <td>50.78</td>
+  </tr>
+  <tr>
+    <td>VATEX (Captioning)</td>
+    <td>CIDEr (test)</td>
+    <td>79.73</td>
+  </tr>
+  <tr>
+    <td>MSVD (QA)</td>
+    <td>Accuracy (test)</td>
+    <td>60.22</td>
+  </tr>
+</tbody></table>
+
+#### Mix model (fine-tune on mixture of transfer tasks)
+
+<table>
+  <tbody><tr>
+    <th>Benchmark</th>
+    <th>Metric (split)</th>
+    <th>mix-224</th>
+    <th>mix-448</th>
+  </tr>
+  <tr>
+    <td><a href="https://arxiv.org/abs/2401.06209">MMVP</a></td>
+    <td>Paired Accuracy</td>
+    <td>46.00</td>
+    <td>45.33</td>
+  </tr>
+  <tr>
+    <td><a href="https://arxiv.org/abs/2305.10355">POPE</a></td>
+    <td>Accuracy<br>(random/popular/adversarial)</td>
+    <td>
+      88.00<br>
+      86.63<br>
+      85.67
+    </td>
+    <td>
+      89.37<br>
+      88.40<br>
+      87.47
+    </td>
+  </tr>
+</tbody></table>
+
+## Ethics and safety
+
+### Evaluation approach
+
+Our evaluation methods include structured evaluations and internal red-teaming
+testing of relevant content policies. Red-teaming was conducted by a number of
+different teams, each with different goals and human evaluation metrics. These
+models were evaluated against a number of different categories relevant to
+ethics and safety, including:
+
+*   Human evaluation on prompts covering child safety, content safety and
+    representational harms. See the [Gemma model
+    card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for
+    more details on evaluation approach, but with image captioning and visual
+    question answering setups.
+*   Image-to-Text benchmark evaluation: Benchmark against relevant academic
+    datasets such as FairFace Dataset ([Karkkainen et al.,
+    2021](https://arxiv.org/abs/1908.04913)).
+
+### Evaluation results
+
+*   The human evaluation results of ethics and safety evaluations are within
+    acceptable thresholds for meeting [internal
+    policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11)
+    for categories such as child safety, content safety and representational
+    harms.
+*   On top of robust internal evaluations, we also use the Perspective API
+    (threshold of 0.8) to measure toxicity, profanity, and other potential
+    issues in the generated captions for images sourced from the FairFace
+    dataset. We report the maximum and median values observed across subgroups
+    for each of the perceived gender, ethnicity, and age attributes.
+
+
+<table>
+  <tbody><tr>
+    </tr></tbody><tbody><tr><th>Metric</th>
+    <th>Perceived<br>gender</th>
+    <th></th>
+    <th>Ethnicity</th>
+    <th></th>
+    <th>Age group</th>
+    <th></th>
+  </tr>
+  <tr>
+    <th></th>
+    <th>Maximum</th>
+    <th>Median</th>
+    <th>Maximum</th>
+    <th>Median</th>
+    <th>Maximum</th>
+    <th>Median</th>
+  </tr>
+  <tr>
+    <td>Toxicity</td>
+    <td>0.04%</td>
+    <td>0.03%</td>
+    <td>0.08%</td>
+    <td>0.00%</td>
+    <td>0.09%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Identity Attack</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Insult</td>
+    <td>0.06%</td>
+    <td>0.04%</td>
+    <td>0.09%</td>
+    <td>0.07%</td>
+    <td>0.16%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Threat</td>
+    <td>0.06%</td>
+    <td>0.05%</td>
+    <td>0.14%</td>
+    <td>0.05%</td>
+    <td>0.17%</td>
+    <td>0.00%</td>
+  </tr>
+  <tr>
+    <td>Profanity</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+    <td>0.00%</td>
+  </tr>
+</tbody></table>
+
+## Usage and limitations
+
+### Intended usage
+
+Open Vision Language Models (VLMs) have a wide range of applications across
+various industries and domains. The following list of potential uses is not
+comprehensive. The purpose of this list is to provide contextual information
+about the possible use-cases that the model creators considered as part of model
+training and development.
+
+Fine-tune on specific vision-language task:
+
+*   The pre-trained models can be fine-tuned on a wide range of vision-language
+    tasks such as: image captioning, short video caption, visual question
+    answering, text reading, object detection and object segmentation.
+*   The pre-trained models can be fine-tuned for specific domains such as remote
+    sensing question answering, visual questions from people who are blind,
+    science question answering, describe UI element functionalities.
+*   The pre-trained models can be fine-tuned for tasks with non-textual outputs
+    such as bounding boxes or segmentation masks.
+
+Vision-language research:
+
+*   The pre-trained models and fine-tuned models can serve as a foundation for researchers to experiment with VLM
+    techniques, develop algorithms, and contribute to the advancement of the
+    field.
+
+### Ethical considerations and risks
+
+The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
+
+*   Bias and Fairness
+    *   VLMs trained on large-scale, real-world image-text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card.
+*   Misinformation and Misuse
+    *   VLMs can be misused to generate text that is false, misleading, or harmful.
+    *   Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](https://ai.google.dev/responsible).
+*   Transparency and Accountability
+    *   This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
+    *   A responsibly developed open model offers the opportunity to share innovation by making VLM technology accessible to developers and researchers across the AI ecosystem.
+
+
+Risks identified and mitigations:
+
+*   **Perpetuation of biases:** It's encouraged to perform continuous monitoring
+    (using evaluation metrics, human review) and the exploration of de-biasing
+    techniques during model training, fine-tuning, and other use cases.
+*   **Generation of harmful content:** Mechanisms and guidelines for content
+    safety are essential. Developers are encouraged to exercise caution and
+    implement appropriate content safety safeguards based on their specific
+    product policies and application use cases.
+*   **Misuse for malicious purposes:** Technical limitations and developer and
+    end-user education can help mitigate against malicious applications of LLMs.
+    Educational resources and reporting mechanisms for users to flag misuse are
+    provided. Prohibited uses of Gemma models are outlined in the [Gemma
+    Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
+*   **Privacy violations:** Models were trained on data filtered to remove certain personal information and sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
+
+### Limitations
+
+*   Most limitations inherited from the underlying Gemma model still apply:
+    *   VLMs are better at tasks that can be framed with clear prompts and
+        instructions. Open-ended or highly complex tasks might be challenging.
+    *   Natural language is inherently complex. VLMs might struggle to grasp
+        subtle nuances, sarcasm, or figurative language.
+    *   VLMs generate responses based on information they learned from their
+        training datasets, but they are not knowledge bases. They may generate
+        incorrect or outdated factual statements.
+    *   VLMs rely on statistical patterns in language and images. They might
+        lack the ability to apply common sense reasoning in certain situations.
+*   PaliGemma was designed first and foremost to serve as a general pre-trained
+    model for transfer to specialized tasks. Hence, its "out of the box" or
+    "zero-shot" performance might lag behind models designed specifically for
+    that.
+*   PaliGemma is not a multi-turn chatbot. It is designed for a single round of
+    image and text input.
+
+    ## Citation
+
+    ```bibtex
+    @article{beyer2024paligemma,
+        title={{PaliGemma: A versatile 3B VLM for transfer}},
+        author={Lucas Beyer* and Andreas Steiner* and André Susano Pinto* and Alexander Kolesnikov* and Xiao Wang* and Daniel Salz and Maxim Neumann and Ibrahim Alabdulmohsin and Michael Tschannen and Emanuele Bugliarello and Thomas Unterthiner and Daniel Keysers and Skanda Koppula and Fangyu Liu and Adam Grycner and Alexey Gritsenko and Neil Houlsby and Manoj Kumar and Keran Rong and Julian Eisenschlos and Rishabh Kabra and Matthias Bauer and Matko Bošnjak and Xi Chen and Matthias Minderer and Paul Voigtlaender and Ioana Bica and Ivana Balazevic and Joan Puigcerver and Pinelopi Papalampidi and Olivier Henaff and Xi Xiong and Radu Soricut and Jeremiah Harmsen and Xiaohua Zhai*},
+        year={2024},
+        journal={arXiv preprint arXiv:2407.07726}
+    }
+    ```
+
+
+Find the paper [here](https://arxiv.org/abs/2407.07726).

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 257152
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "final-hf/paligemma-3b-pt-448-main",
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "ignore_index": -100,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "pad_token_id": 0,
+  "projection_dim": 2048,
+  "text_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_image_tokens": 1024,
+    "num_key_value_heads": 1,
+    "torch_dtype": "float32",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 448,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_image_tokens": 1024,
+    "patch_size": 14,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "vision_use_head": false
+  },
+  "vocab_size": 257216
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016569117e00622ec8ff7af9104a66b5e81baf06772674be997e5c41265fde96
+size 4956951424

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f876f1e6915d8abda1652312dc9a0ea7810a137e4996226fc1dfb2ede7ad8109
+size 4999820608

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418030fe594809e40b1d57f3e386122795fc17716a57266db6b32c504e00b07a
+size 1740714288

model.safetensors.index.json

@@ -0,0 +1,610 @@
+{
+  "metadata": {
+    "total_size": 11697404864
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
+    "multi_modal_projector.linear.bias": "model-00001-of-00003.safetensors",
+    "multi_modal_projector.linear.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,40 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format",
+    "do_convert_rgb"
+  ],
+  "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
+  ],
+  "processor_class": "PaliGemmaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6773c135b77b834de1d13c75a4c98ab7a3684ffd602d1831e1f1bf5467c563
+size 17549604

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6
+size 4264023

tokenizer_config.json

@@ -0,0 +1,1764 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "257152": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PaliGemmaProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}