Add action tokens and update config

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/README.md

@@ -0,0 +1,270 @@
+---
+library_name: transformers
+license: apache-2.0
+datasets:
+- HuggingFaceM4/the_cauldron
+- HuggingFaceM4/Docmatix
+- lmms-lab/LLaVA-OneVision-Data
+- lmms-lab/M4-Instruct-Data
+- HuggingFaceFV/finevideo
+- MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
+- lmms-lab/LLaVA-Video-178K
+- orrzohar/Video-STaR
+- Mutonix/Vript
+- TIGER-Lab/VISTA-400K
+- Enxin/MovieChat-1K_train
+- ShareGPT4Video/ShareGPT4Video
+pipeline_tag: image-text-to-text
+language:
+- en
+base_model:
+- HuggingFaceTB/SmolVLM-500M-Instruct
+---
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM2_banner.png" width="800" height="auto" alt="Image description">
+
+# SmolVLM2-500M-Video
+
+SmolVLM2-500M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.8GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks. This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited.
+## Model Summary
+
+- **Developed by:** Hugging Face 🤗
+- **Model type:** Multi-modal model (image/multi-image/video/text)
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
+
+## Resources
+
+- **Demo:** [Video Highlight Generator](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM2-HighlightGenerator)
+- **Blog:** [Blog post](https://huggingface.co/blog/smolvlm2)
+
+## Uses
+
+SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input consists of text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation.
+
+To fine-tune SmolVLM2 on a specific task, you can follow [the fine-tuning tutorial](https://github.com/huggingface/smollm/blob/main/vision/finetuning/Smol_VLM_FT.ipynb).
+
+## Evaluation 
+
+We evaluated the performance of the SmolVLM2 family on the following scientific benchmarks:
+
+| Size    | Video-MME | MLVU | MVBench |
+|----------|-----------------|----------|---------------|
+| 2.2B   | 52.1            | 55.2     | 46.27        |
+| 500M | 42.2            | 47.3     | 39.73        |
+| 256M | 33.7            | 40.6     | 32.7          |
+
+
+### How to get started
+
+You can use transformers to load, infer and fine-tune SmolVLM. Make sure you have num2words, flash-attn and latest transformers installed.
+You can load the model as follows.
+
+```python
+from transformers import AutoProcessor, AutoModelForImageTextToText
+import torch
+
+model_path = "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
+processor = AutoProcessor.from_pretrained(model_path)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_path,
+    torch_dtype=torch.bfloat16,
+    _attn_implementation="flash_attention_2"
+).to("cuda")
+```
+
+#### Simple Inference
+
+You preprocess your inputs directly using chat templates and directly passing them 
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+            {"type": "text", "text": "Can you describe this image?"},
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+print(generated_texts[0])
+```
+
+#### Video Inference
+
+To use SmolVLM2 for video inference, make sure you have decord installed. 
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "video", "path": "path_to_video.mp4"},
+            {"type": "text", "text": "Describe this video in detail"}
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+
+print(generated_texts[0])
+```
+#### Multi-image Interleaved Inference
+
+You can interleave multiple media with text using chat templates.
+
+```python
+import torch
+
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+          {"type": "text", "text": "What is the similarity between these two images?"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"},            
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+print(generated_texts[0])
+```
+
+
+### Model optimizations
+
+## Misuse and Out-of-scope Use
+
+SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
+
+- Prohibited Uses:
+  - Evaluating or scoring individuals (e.g., in employment, education, credit)
+  - Critical automated decision-making
+  - Generating unreliable factual content
+- Malicious Activities:
+  - Spam generation
+  - Disinformation campaigns
+  - Harassment or abuse
+  - Unauthorized surveillance
+
+### License
+
+SmolVLM2 is built upon [SigLIP](https://huggingface.co/google/siglip-base-patch16-512) as image encoder and [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) for text decoder part.
+
+We release the SmolVLM2 checkpoints under the Apache 2.0 license.
+
+## Citation information
+You can cite us in the following way:
+```bibtex
+@article{marafioti2025smolvlm,
+  title={SmolVLM: Redefining small and efficient multimodal models}, 
+  author={Andrés Marafioti and Orr Zohar and Miquel Farré and Merve Noyan and Elie Bakouch and Pedro Cuenca and Cyril Zakka and Loubna Ben Allal and Anton Lozhkov and Nouamane Tazi and Vaibhav Srivastav and Joshua Lochner and Hugo Larcher and Mathieu Morlon and Lewis Tunstall and Leandro von Werra and Thomas Wolf},
+  journal={arXiv preprint arXiv:2504.05299},
+  year={2025}
+}
+```
+
+## Training Data
+SmolVLM2 used 3.3M samples for training originally from ten different datasets: [LlaVa Onevision](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), [M4-Instruct](https://huggingface.co/datasets/lmms-lab/M4-Instruct-Data), [Mammoth](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M), [LlaVa Video 178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K), [FineVideo](https://huggingface.co/datasets/HuggingFaceFV/finevideo), [VideoStar](https://huggingface.co/datasets/orrzohar/Video-STaR), [VRipt](https://huggingface.co/datasets/Mutonix/Vript), [Vista-400K](https://huggingface.co/datasets/TIGER-Lab/VISTA-400K), [MovieChat](https://huggingface.co/datasets/Enxin/MovieChat-1K_train) and [ShareGPT4Video](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video).
+In the following plots we give a general overview of the samples across modalities and the source of those samples.
+<!--
+<center><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_data_split.png" width="auto" height="auto" alt="Image description">
+</center>
+
+### Details
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_datadetails.png" width="auto" height="auto" alt="Image description"> -->
+
+## Data Split per modality
+
+| Data Type    | Percentage |
+|--------------|------------|
+| Image        | 34.4%      |
+| Text         | 20.2%      |
+| Video        | 33.0%      |
+| Multi-image  | 12.3%      |
+
+
+## Granular dataset slices per modality
+
+### Text Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-onevision/magpie_pro_ft3_80b_mt      | 6.8%       |
+| llava-onevision/magpie_pro_ft3_80b_tt      | 6.8%       |
+| llava-onevision/magpie_pro_qwen2_72b_tt    | 5.8%       |
+| llava-onevision/mathqa                     | 0.9%       |
+
+### Multi-image Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| m4-instruct-data/m4_instruct_multiimage    | 10.4%      |
+| mammoth/multiimage-cap6                    | 1.9%       |
+
+### Image Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-onevision/other                      | 17.4%      |
+| llava-onevision/vision_flan                | 3.9%       |
+| llava-onevision/mavis_math_metagen         | 2.6%       |
+| llava-onevision/mavis_math_rule_geo        | 2.5%       |
+| llava-onevision/sharegpt4o                 | 1.7%       |
+| llava-onevision/sharegpt4v_coco            | 1.5%       |
+| llava-onevision/image_textualization       | 1.3%       |
+| llava-onevision/sharegpt4v_llava           | 0.9%       |
+| llava-onevision/mapqa                      | 0.9%       |
+| llava-onevision/qa                         | 0.8%       |
+| llava-onevision/textocr                    | 0.8%       |
+
+### Video Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-video-178k/1-2m                      | 7.3%       |
+| llava-video-178k/2-3m                      | 7.0%       |
+| other-video/combined                       | 5.7%       |
+| llava-video-178k/hound                     | 4.4%       |
+| llava-video-178k/0-30s                     | 2.4%       |
+| video-star/starb                           | 2.2%       |
+| vista-400k/combined                        | 2.2%       |
+| vript/long                                 | 1.0%       |
+| ShareGPT4Video/all                         | 0.8%       |

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/added_tokens.json

@@ -0,0 +1,386 @@
+{
+  "<action_0>": 49280,
+  "<action_100>": 49380,
+  "<action_101>": 49381,
+  "<action_102>": 49382,
+  "<action_103>": 49383,
+  "<action_104>": 49384,
+  "<action_105>": 49385,
+  "<action_106>": 49386,
+  "<action_107>": 49387,
+  "<action_108>": 49388,
+  "<action_109>": 49389,
+  "<action_10>": 49290,
+  "<action_110>": 49390,
+  "<action_111>": 49391,
+  "<action_112>": 49392,
+  "<action_113>": 49393,
+  "<action_114>": 49394,
+  "<action_115>": 49395,
+  "<action_116>": 49396,
+  "<action_117>": 49397,
+  "<action_118>": 49398,
+  "<action_119>": 49399,
+  "<action_11>": 49291,
+  "<action_120>": 49400,
+  "<action_121>": 49401,
+  "<action_122>": 49402,
+  "<action_123>": 49403,
+  "<action_124>": 49404,
+  "<action_125>": 49405,
+  "<action_126>": 49406,
+  "<action_127>": 49407,
+  "<action_128>": 49408,
+  "<action_129>": 49409,
+  "<action_12>": 49292,
+  "<action_130>": 49410,
+  "<action_131>": 49411,
+  "<action_132>": 49412,
+  "<action_133>": 49413,
+  "<action_134>": 49414,
+  "<action_135>": 49415,
+  "<action_136>": 49416,
+  "<action_137>": 49417,
+  "<action_138>": 49418,
+  "<action_139>": 49419,
+  "<action_13>": 49293,
+  "<action_140>": 49420,
+  "<action_141>": 49421,
+  "<action_142>": 49422,
+  "<action_143>": 49423,
+  "<action_144>": 49424,
+  "<action_145>": 49425,
+  "<action_146>": 49426,
+  "<action_147>": 49427,
+  "<action_148>": 49428,
+  "<action_149>": 49429,
+  "<action_14>": 49294,
+  "<action_150>": 49430,
+  "<action_151>": 49431,
+  "<action_152>": 49432,
+  "<action_153>": 49433,
+  "<action_154>": 49434,
+  "<action_155>": 49435,
+  "<action_156>": 49436,
+  "<action_157>": 49437,
+  "<action_158>": 49438,
+  "<action_159>": 49439,
+  "<action_15>": 49295,
+  "<action_160>": 49440,
+  "<action_161>": 49441,
+  "<action_162>": 49442,
+  "<action_163>": 49443,
+  "<action_164>": 49444,
+  "<action_165>": 49445,
+  "<action_166>": 49446,
+  "<action_167>": 49447,
+  "<action_168>": 49448,
+  "<action_169>": 49449,
+  "<action_16>": 49296,
+  "<action_170>": 49450,
+  "<action_171>": 49451,
+  "<action_172>": 49452,
+  "<action_173>": 49453,
+  "<action_174>": 49454,
+  "<action_175>": 49455,
+  "<action_176>": 49456,
+  "<action_177>": 49457,
+  "<action_178>": 49458,
+  "<action_179>": 49459,
+  "<action_17>": 49297,
+  "<action_180>": 49460,
+  "<action_181>": 49461,
+  "<action_182>": 49462,
+  "<action_183>": 49463,
+  "<action_184>": 49464,
+  "<action_185>": 49465,
+  "<action_186>": 49466,
+  "<action_187>": 49467,
+  "<action_188>": 49468,
+  "<action_189>": 49469,
+  "<action_18>": 49298,
+  "<action_190>": 49470,
+  "<action_191>": 49471,
+  "<action_192>": 49472,
+  "<action_193>": 49473,
+  "<action_194>": 49474,
+  "<action_195>": 49475,
+  "<action_196>": 49476,
+  "<action_197>": 49477,
+  "<action_198>": 49478,
+  "<action_199>": 49479,
+  "<action_19>": 49299,
+  "<action_1>": 49281,
+  "<action_200>": 49480,
+  "<action_201>": 49481,
+  "<action_202>": 49482,
+  "<action_203>": 49483,
+  "<action_204>": 49484,
+  "<action_205>": 49485,
+  "<action_206>": 49486,
+  "<action_207>": 49487,
+  "<action_208>": 49488,
+  "<action_209>": 49489,
+  "<action_20>": 49300,
+  "<action_210>": 49490,
+  "<action_211>": 49491,
+  "<action_212>": 49492,
+  "<action_213>": 49493,
+  "<action_214>": 49494,
+  "<action_215>": 49495,
+  "<action_216>": 49496,
+  "<action_217>": 49497,
+  "<action_218>": 49498,
+  "<action_219>": 49499,
+  "<action_21>": 49301,
+  "<action_220>": 49500,
+  "<action_221>": 49501,
+  "<action_222>": 49502,
+  "<action_223>": 49503,
+  "<action_224>": 49504,
+  "<action_225>": 49505,
+  "<action_226>": 49506,
+  "<action_227>": 49507,
+  "<action_228>": 49508,
+  "<action_229>": 49509,
+  "<action_22>": 49302,
+  "<action_230>": 49510,
+  "<action_231>": 49511,
+  "<action_232>": 49512,
+  "<action_233>": 49513,
+  "<action_234>": 49514,
+  "<action_235>": 49515,
+  "<action_236>": 49516,
+  "<action_237>": 49517,
+  "<action_238>": 49518,
+  "<action_239>": 49519,
+  "<action_23>": 49303,
+  "<action_240>": 49520,
+  "<action_241>": 49521,
+  "<action_242>": 49522,
+  "<action_243>": 49523,
+  "<action_244>": 49524,
+  "<action_245>": 49525,
+  "<action_246>": 49526,
+  "<action_247>": 49527,
+  "<action_248>": 49528,
+  "<action_249>": 49529,
+  "<action_24>": 49304,
+  "<action_250>": 49530,
+  "<action_251>": 49531,
+  "<action_252>": 49532,
+  "<action_253>": 49533,
+  "<action_254>": 49534,
+  "<action_255>": 49535,
+  "<action_25>": 49305,
+  "<action_26>": 49306,
+  "<action_27>": 49307,
+  "<action_28>": 49308,
+  "<action_29>": 49309,
+  "<action_2>": 49282,
+  "<action_30>": 49310,
+  "<action_31>": 49311,
+  "<action_32>": 49312,
+  "<action_33>": 49313,
+  "<action_34>": 49314,
+  "<action_35>": 49315,
+  "<action_36>": 49316,
+  "<action_37>": 49317,
+  "<action_38>": 49318,
+  "<action_39>": 49319,
+  "<action_3>": 49283,
+  "<action_40>": 49320,
+  "<action_41>": 49321,
+  "<action_42>": 49322,
+  "<action_43>": 49323,
+  "<action_44>": 49324,
+  "<action_45>": 49325,
+  "<action_46>": 49326,
+  "<action_47>": 49327,
+  "<action_48>": 49328,
+  "<action_49>": 49329,
+  "<action_4>": 49284,
+  "<action_50>": 49330,
+  "<action_51>": 49331,
+  "<action_52>": 49332,
+  "<action_53>": 49333,
+  "<action_54>": 49334,
+  "<action_55>": 49335,
+  "<action_56>": 49336,
+  "<action_57>": 49337,
+  "<action_58>": 49338,
+  "<action_59>": 49339,
+  "<action_5>": 49285,
+  "<action_60>": 49340,
+  "<action_61>": 49341,
+  "<action_62>": 49342,
+  "<action_63>": 49343,
+  "<action_64>": 49344,
+  "<action_65>": 49345,
+  "<action_66>": 49346,
+  "<action_67>": 49347,
+  "<action_68>": 49348,
+  "<action_69>": 49349,
+  "<action_6>": 49286,
+  "<action_70>": 49350,
+  "<action_71>": 49351,
+  "<action_72>": 49352,
+  "<action_73>": 49353,
+  "<action_74>": 49354,
+  "<action_75>": 49355,
+  "<action_76>": 49356,
+  "<action_77>": 49357,
+  "<action_78>": 49358,
+  "<action_79>": 49359,
+  "<action_7>": 49287,
+  "<action_80>": 49360,
+  "<action_81>": 49361,
+  "<action_82>": 49362,
+  "<action_83>": 49363,
+  "<action_84>": 49364,
+  "<action_85>": 49365,
+  "<action_86>": 49366,
+  "<action_87>": 49367,
+  "<action_88>": 49368,
+  "<action_89>": 49369,
+  "<action_8>": 49288,
+  "<action_90>": 49370,
+  "<action_91>": 49371,
+  "<action_92>": 49372,
+  "<action_93>": 49373,
+  "<action_94>": 49374,
+  "<action_95>": 49375,
+  "<action_96>": 49376,
+  "<action_97>": 49377,
+  "<action_98>": 49378,
+  "<action_99>": 49379,
+  "<action_9>": 49289,
+  "<end_of_utterance>": 49279,
+  "<fake_token_around_image>": 49189,
+  "<global-img>": 49152,
+  "<image>": 49190,
+  "<row_1_col_1>": 49153,
+  "<row_1_col_2>": 49154,
+  "<row_1_col_3>": 49155,
+  "<row_1_col_4>": 49156,
+  "<row_1_col_5>": 49157,
+  "<row_1_col_6>": 49158,
+  "<row_2_col_1>": 49159,
+  "<row_2_col_2>": 49160,
+  "<row_2_col_3>": 49161,
+  "<row_2_col_4>": 49162,
+  "<row_2_col_5>": 49163,
+  "<row_2_col_6>": 49164,
+  "<row_3_col_1>": 49165,
+  "<row_3_col_2>": 49166,
+  "<row_3_col_3>": 49167,
+  "<row_3_col_4>": 49168,
+  "<row_3_col_5>": 49169,
+  "<row_3_col_6>": 49170,
+  "<row_4_col_1>": 49171,
+  "<row_4_col_2>": 49172,
+  "<row_4_col_3>": 49173,
+  "<row_4_col_4>": 49174,
+  "<row_4_col_5>": 49175,
+  "<row_4_col_6>": 49176,
+  "<row_5_col_1>": 49177,
+  "<row_5_col_2>": 49178,
+  "<row_5_col_3>": 49179,
+  "<row_5_col_4>": 49180,
+  "<row_5_col_5>": 49181,
+  "<row_5_col_6>": 49182,
+  "<row_6_col_1>": 49183,
+  "<row_6_col_2>": 49184,
+  "<row_6_col_3>": 49185,
+  "<row_6_col_4>": 49186,
+  "<row_6_col_5>": 49187,
+  "<row_6_col_6>": 49188,
+  "<|reserved_special_token_0|>": 49191,
+  "<|reserved_special_token_10|>": 49201,
+  "<|reserved_special_token_11|>": 49202,
+  "<|reserved_special_token_12|>": 49203,
+  "<|reserved_special_token_13|>": 49204,
+  "<|reserved_special_token_14|>": 49205,
+  "<|reserved_special_token_15|>": 49206,
+  "<|reserved_special_token_16|>": 49207,
+  "<|reserved_special_token_17|>": 49208,
+  "<|reserved_special_token_18|>": 49209,
+  "<|reserved_special_token_19|>": 49210,
+  "<|reserved_special_token_1|>": 49192,
+  "<|reserved_special_token_20|>": 49211,
+  "<|reserved_special_token_21|>": 49212,
+  "<|reserved_special_token_22|>": 49213,
+  "<|reserved_special_token_23|>": 49214,
+  "<|reserved_special_token_24|>": 49215,
+  "<|reserved_special_token_25|>": 49216,
+  "<|reserved_special_token_26|>": 49217,
+  "<|reserved_special_token_27|>": 49218,
+  "<|reserved_special_token_28|>": 49219,
+  "<|reserved_special_token_29|>": 49220,
+  "<|reserved_special_token_2|>": 49193,
+  "<|reserved_special_token_30|>": 49221,
+  "<|reserved_special_token_31|>": 49222,
+  "<|reserved_special_token_32|>": 49223,
+  "<|reserved_special_token_33|>": 49224,
+  "<|reserved_special_token_34|>": 49225,
+  "<|reserved_special_token_35|>": 49226,
+  "<|reserved_special_token_36|>": 49227,
+  "<|reserved_special_token_37|>": 49228,
+  "<|reserved_special_token_38|>": 49229,
+  "<|reserved_special_token_39|>": 49230,
+  "<|reserved_special_token_3|>": 49194,
+  "<|reserved_special_token_40|>": 49231,
+  "<|reserved_special_token_41|>": 49232,
+  "<|reserved_special_token_42|>": 49233,
+  "<|reserved_special_token_43|>": 49234,
+  "<|reserved_special_token_44|>": 49235,
+  "<|reserved_special_token_45|>": 49236,
+  "<|reserved_special_token_46|>": 49237,
+  "<|reserved_special_token_47|>": 49238,
+  "<|reserved_special_token_48|>": 49239,
+  "<|reserved_special_token_49|>": 49240,
+  "<|reserved_special_token_4|>": 49195,
+  "<|reserved_special_token_50|>": 49241,
+  "<|reserved_special_token_51|>": 49242,
+  "<|reserved_special_token_52|>": 49243,
+  "<|reserved_special_token_53|>": 49244,
+  "<|reserved_special_token_54|>": 49245,
+  "<|reserved_special_token_55|>": 49246,
+  "<|reserved_special_token_56|>": 49247,
+  "<|reserved_special_token_57|>": 49248,
+  "<|reserved_special_token_58|>": 49249,
+  "<|reserved_special_token_59|>": 49250,
+  "<|reserved_special_token_5|>": 49196,
+  "<|reserved_special_token_60|>": 49251,
+  "<|reserved_special_token_61|>": 49252,
+  "<|reserved_special_token_62|>": 49253,
+  "<|reserved_special_token_63|>": 49254,
+  "<|reserved_special_token_64|>": 49255,
+  "<|reserved_special_token_65|>": 49256,
+  "<|reserved_special_token_66|>": 49257,
+  "<|reserved_special_token_67|>": 49258,
+  "<|reserved_special_token_68|>": 49259,
+  "<|reserved_special_token_69|>": 49260,
+  "<|reserved_special_token_6|>": 49197,
+  "<|reserved_special_token_70|>": 49261,
+  "<|reserved_special_token_71|>": 49262,
+  "<|reserved_special_token_72|>": 49263,
+  "<|reserved_special_token_73|>": 49264,
+  "<|reserved_special_token_74|>": 49265,
+  "<|reserved_special_token_75|>": 49266,
+  "<|reserved_special_token_76|>": 49267,
+  "<|reserved_special_token_77|>": 49268,
+  "<|reserved_special_token_78|>": 49269,
+  "<|reserved_special_token_79|>": 49270,
+  "<|reserved_special_token_7|>": 49198,
+  "<|reserved_special_token_80|>": 49271,
+  "<|reserved_special_token_81|>": 49272,
+  "<|reserved_special_token_82|>": 49273,
+  "<|reserved_special_token_83|>": 49274,
+  "<|reserved_special_token_84|>": 49275,
+  "<|reserved_special_token_85|>": 49276,
+  "<|reserved_special_token_86|>": 49277,
+  "<|reserved_special_token_87|>": 49278,
+  "<|reserved_special_token_8|>": 49199,
+  "<|reserved_special_token_9|>": 49200
+}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/chat_template.jinja

@@ -0,0 +1,2 @@
+<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
+{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}"
+}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/config.json

@@ -0,0 +1,141 @@
+{
+  "architectures": [
+    "SmolVLMForConditionalGeneration"
+  ],
+  "image_token_id": 49190,
+  "model_type": "smolvlm",
+  "pad_token_id": 128002,
+  "scale_factor": 4,
+  "text_config": {
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "head_dim": 64,
+    "hidden_size": 960,
+    "intermediate_size": 2560,
+    "is_llama_config": true,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_attention_heads": 15,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 5,
+    "pad_token_id": 2,
+    "perceiver_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "vllama3",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_key_value_heads": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "qk_layer_norms_perceiver": false,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resampler_depth": 6,
+      "resampler_head_dim": 96,
+      "resampler_n_heads": 16,
+      "resampler_n_latents": 64,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.46.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "pixel_shuffle_factor": 4,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_interleaved": false,
+    "rope_theta": 100000,
+    "torch_dtype": "bfloat16",
+    "transformers.js_config": {
+      "kv_cache_dtype": {
+        "fp16": "float16",
+        "q4f16": "float16"
+      }
+    },
+    "use_resampler": false,
+    "vocab_size": 49536
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_reentrant_checkpointing": false,
+  "vision_config": {
+    "hidden_size": 768,
+    "image_size": 512,
+    "max_image_size": {
+      "longest_edge": 512
+    },
+    "model_type": "smolvlm_vision",
+    "num_attention_heads": 12,
+    "patch_size": 16,
+    "size": {
+      "longest_edge": 512
+    },
+    "tie_word_embeddings": false,
+    "use_base_siglip": false
+  },
+  "vocab_size": 49536
+}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 49279,
+  "pad_token_id": 2,
+  "transformers_version": "4.47.1"
+}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bfd456c9472c0acd5719d6e514c4b859891af205ee1a736552fd3497b8b0c3
+size 2029990624

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8743f020606f401ffa0c0ec7a7055da6ad7518b981ecdb060b62da3a60ec45
+size 1450426001

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20111c92ecee932e85de34e0afd9341f60bb210456bc5d8a4809c055dd5bc15
+size 206503532

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace259f4ff3a070cfcefc41c6b4ddaf52a5c1b988348004da13043ff4a6de5ae
+size 725489385

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0a356562c7e474012c5e383de58d44d487a517c04190d26e5891db86cb2b1f
+size 365039224

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69561703c23810bf58cd4fe81b2427df95339a5b55743f62d1e767bd4a83a1e2
+size 229119396

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6265f0aa571ad624f67b5f19b79f1562b4bfd4e6db812815c1794172985b3e5e
+size 205328508

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5aaa12d62d43a05a4a7456864c508d0b3c17c55a654c05fb568f6da0b7d212d
+size 365039344

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/decoder_model_merged_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5aaa12d62d43a05a4a7456864c508d0b3c17c55a654c05fb568f6da0b7d212d
+size 365039344

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4696831e7181d72fd7736b0c119cd53141a46c940ca24c03ce05ba623b402dd4
+size 189235499

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc09c2b3264365dcc8de8cae7513b640a40624cd038ede20a0ffcac0f82ecb11
+size 189235518

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9e790f2e90ebf3b1efe84ec82530d6c12e27b0a103703fe865a5faf24f2336
+size 94617986

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6d275190cd1cdf3339225b98b42116871ddc4e0c3210801f02bf2a1d2e164a
+size 47309344

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc09c2b3264365dcc8de8cae7513b640a40624cd038ede20a0ffcac0f82ecb11
+size 189235518

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a330cc444671c47e6a2de559405404043b2a49b015188250eca8c0c88d263b73
+size 94618005

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6d275190cd1cdf3339225b98b42116871ddc4e0c3210801f02bf2a1d2e164a
+size 47309344

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/embed_tokens_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6d275190cd1cdf3339225b98b42116871ddc4e0c3210801f02bf2a1d2e164a
+size 47309344

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4797cdad0ba1958e7dfcc5e074d0b02ae3c4df80cce17ecab282dde37e0ddc1
+size 393190822

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749b03c76adc0311fdc2d347ace3c9f78c792816e519c3e28a17f12f27cd496d
+size 60688904

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faa8f3b4a922514a2e7773f20e99fdf7dc7b4eeeeaca1fb82cf18f7945ca23a
+size 196731834

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d931eb204e21ab4d905d62976aeaefe20360076f52760ba55b84a5b35088284f
+size 98966476

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb71423919f04851bdac96588267e6a9db95903ca94fcd7b7a0f51b5cd53d8a
+size 66734064

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e811e4cef2c214c80ea7572eacb102ea396a881fb9170577b20c10fe4fa485
+size 57691749

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8e2950e6837a71a3d972a14eb287d8875c4c2d5e8cfd6001bf185115295cdd
+size 98966521

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/onnx/vision_encoder_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8e2950e6837a71a3d972a14eb287d8875c4c2d5e8cfd6001bf185115295cdd
+size 98966521

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/preprocessor_config.json

@@ -0,0 +1,35 @@
+{
+  "do_convert_rgb": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SmolVLMImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_size": {
+    "longest_edge": 512
+  },
+  "processor_class": "SmolVLMProcessor",
+  "resample": 1,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 512
+  },
+  "video_sampling": {
+    "fps": 1,
+    "max_frames": 64,
+    "video_size": {
+      "longest_edge": 512
+    }
+  }
+}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/processor_config.json

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

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/special_tokens_map.json

@@ -0,0 +1,78 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<action_250>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<action_251>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<action_252>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<action_253>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<action_254>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<action_255>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "end_of_utterance_token": "<end_of_utterance>",
+  "eos_token": {
+    "content": "<end_of_utterance>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "fake_image_token": "<fake_token_around_image>",
+  "global_image_token": "<global-img>",
+  "image_token": "<image>",
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

HuggingFaceTB_SmolVLM2-500M-Video-Instruct/tokenizer_config.json

@@ -0,0 +1,3242 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<global-img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<row_1_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<row_1_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49155": {
+      "content": "<row_1_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49156": {
+      "content": "<row_1_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49157": {
+      "content": "<row_1_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49158": {
+      "content": "<row_1_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49159": {
+      "content": "<row_2_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49160": {
+      "content": "<row_2_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49161": {
+      "content": "<row_2_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49162": {
+      "content": "<row_2_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49163": {
+      "content": "<row_2_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49164": {
+      "content": "<row_2_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49165": {
+      "content": "<row_3_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49166": {
+      "content": "<row_3_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49167": {
+      "content": "<row_3_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49168": {
+      "content": "<row_3_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49169": {
+      "content": "<row_3_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49170": {
+      "content": "<row_3_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49171": {
+      "content": "<row_4_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49172": {
+      "content": "<row_4_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49173": {
+      "content": "<row_4_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49174": {
+      "content": "<row_4_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49175": {
+      "content": "<row_4_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49176": {
+      "content": "<row_4_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49177": {
+      "content": "<row_5_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49178": {
+      "content": "<row_5_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49179": {
+      "content": "<row_5_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49180": {
+      "content": "<row_5_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49181": {
+      "content": "<row_5_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49182": {
+      "content": "<row_5_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49183": {
+      "content": "<row_6_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49184": {
+      "content": "<row_6_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49185": {
+      "content": "<row_6_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49186": {
+      "content": "<row_6_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49187": {
+      "content": "<row_6_col_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49188": {
+      "content": "<row_6_col_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49189": {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49190": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49191": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49192": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49193": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49194": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49195": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49196": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49197": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49198": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49199": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49200": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49201": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49202": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49203": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49204": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49205": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49206": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49207": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49208": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49209": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49210": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49211": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49212": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49213": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49214": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49215": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49216": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49217": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49218": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49219": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49220": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49221": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49222": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49223": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49224": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49225": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49226": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49227": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49228": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49229": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49230": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49231": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49232": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49233": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49234": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49235": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49236": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49237": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49238": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49239": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49240": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49241": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49242": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49243": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49244": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49245": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49246": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49247": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49248": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49249": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49250": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49251": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49252": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49253": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49254": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49255": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49256": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49257": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49258": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49259": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49260": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49261": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49262": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49263": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49264": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49265": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49266": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49267": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49268": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49269": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49270": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49271": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49272": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49273": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49274": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49275": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49276": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49277": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49278": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49279": {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49280": {
+      "content": "<action_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49281": {
+      "content": "<action_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49282": {
+      "content": "<action_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49283": {
+      "content": "<action_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49284": {
+      "content": "<action_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49285": {
+      "content": "<action_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49286": {
+      "content": "<action_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49287": {
+      "content": "<action_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49288": {
+      "content": "<action_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49289": {
+      "content": "<action_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49290": {
+      "content": "<action_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49291": {
+      "content": "<action_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49292": {
+      "content": "<action_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49293": {
+      "content": "<action_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49294": {
+      "content": "<action_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49295": {
+      "content": "<action_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49296": {
+      "content": "<action_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49297": {
+      "content": "<action_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49298": {
+      "content": "<action_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49299": {
+      "content": "<action_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49300": {
+      "content": "<action_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49301": {
+      "content": "<action_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49302": {
+      "content": "<action_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49303": {
+      "content": "<action_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49304": {
+      "content": "<action_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49305": {
+      "content": "<action_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49306": {
+      "content": "<action_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49307": {
+      "content": "<action_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49308": {
+      "content": "<action_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49309": {
+      "content": "<action_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49310": {
+      "content": "<action_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49311": {
+      "content": "<action_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49312": {
+      "content": "<action_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49313": {
+      "content": "<action_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49314": {
+      "content": "<action_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49315": {
+      "content": "<action_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49316": {
+      "content": "<action_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49317": {
+      "content": "<action_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49318": {
+      "content": "<action_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49319": {
+      "content": "<action_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49320": {
+      "content": "<action_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49321": {
+      "content": "<action_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49322": {
+      "content": "<action_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49323": {
+      "content": "<action_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49324": {
+      "content": "<action_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49325": {
+      "content": "<action_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49326": {
+      "content": "<action_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49327": {
+      "content": "<action_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49328": {
+      "content": "<action_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49329": {
+      "content": "<action_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49330": {
+      "content": "<action_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49331": {
+      "content": "<action_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49332": {
+      "content": "<action_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49333": {
+      "content": "<action_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49334": {
+      "content": "<action_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49335": {
+      "content": "<action_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49336": {
+      "content": "<action_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49337": {
+      "content": "<action_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49338": {
+      "content": "<action_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49339": {
+      "content": "<action_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49340": {
+      "content": "<action_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49341": {
+      "content": "<action_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49342": {
+      "content": "<action_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49343": {
+      "content": "<action_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49344": {
+      "content": "<action_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49345": {
+      "content": "<action_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49346": {
+      "content": "<action_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49347": {
+      "content": "<action_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49348": {
+      "content": "<action_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49349": {
+      "content": "<action_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49350": {
+      "content": "<action_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49351": {
+      "content": "<action_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49352": {
+      "content": "<action_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49353": {
+      "content": "<action_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49354": {
+      "content": "<action_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49355": {
+      "content": "<action_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49356": {
+      "content": "<action_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49357": {
+      "content": "<action_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49358": {
+      "content": "<action_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49359": {
+      "content": "<action_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49360": {
+      "content": "<action_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49361": {
+      "content": "<action_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49362": {
+      "content": "<action_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49363": {
+      "content": "<action_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49364": {
+      "content": "<action_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49365": {
+      "content": "<action_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49366": {
+      "content": "<action_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49367": {
+      "content": "<action_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49368": {
+      "content": "<action_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49369": {
+      "content": "<action_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49370": {
+      "content": "<action_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49371": {
+      "content": "<action_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49372": {
+      "content": "<action_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49373": {
+      "content": "<action_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49374": {
+      "content": "<action_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49375": {
+      "content": "<action_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49376": {
+      "content": "<action_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49377": {
+      "content": "<action_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49378": {
+      "content": "<action_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49379": {
+      "content": "<action_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49380": {
+      "content": "<action_100>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49381": {
+      "content": "<action_101>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49382": {
+      "content": "<action_102>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49383": {
+      "content": "<action_103>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49384": {
+      "content": "<action_104>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49385": {
+      "content": "<action_105>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49386": {
+      "content": "<action_106>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49387": {
+      "content": "<action_107>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49388": {
+      "content": "<action_108>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49389": {
+      "content": "<action_109>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49390": {
+      "content": "<action_110>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49391": {
+      "content": "<action_111>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49392": {
+      "content": "<action_112>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49393": {
+      "content": "<action_113>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49394": {
+      "content": "<action_114>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49395": {
+      "content": "<action_115>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49396": {
+      "content": "<action_116>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49397": {
+      "content": "<action_117>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49398": {
+      "content": "<action_118>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49399": {
+      "content": "<action_119>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49400": {
+      "content": "<action_120>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49401": {
+      "content": "<action_121>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49402": {
+      "content": "<action_122>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49403": {
+      "content": "<action_123>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49404": {
+      "content": "<action_124>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49405": {
+      "content": "<action_125>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<action_126>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<action_127>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49408": {
+      "content": "<action_128>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49409": {
+      "content": "<action_129>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49410": {
+      "content": "<action_130>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49411": {
+      "content": "<action_131>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49412": {
+      "content": "<action_132>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49413": {
+      "content": "<action_133>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49414": {
+      "content": "<action_134>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49415": {
+      "content": "<action_135>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49416": {
+      "content": "<action_136>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49417": {
+      "content": "<action_137>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49418": {
+      "content": "<action_138>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49419": {
+      "content": "<action_139>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49420": {
+      "content": "<action_140>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49421": {
+      "content": "<action_141>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49422": {
+      "content": "<action_142>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49423": {
+      "content": "<action_143>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49424": {
+      "content": "<action_144>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49425": {
+      "content": "<action_145>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49426": {
+      "content": "<action_146>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49427": {
+      "content": "<action_147>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49428": {
+      "content": "<action_148>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49429": {
+      "content": "<action_149>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49430": {
+      "content": "<action_150>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49431": {
+      "content": "<action_151>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49432": {
+      "content": "<action_152>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49433": {
+      "content": "<action_153>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49434": {
+      "content": "<action_154>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49435": {
+      "content": "<action_155>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49436": {
+      "content": "<action_156>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49437": {
+      "content": "<action_157>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49438": {
+      "content": "<action_158>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49439": {
+      "content": "<action_159>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49440": {
+      "content": "<action_160>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49441": {
+      "content": "<action_161>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49442": {
+      "content": "<action_162>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49443": {
+      "content": "<action_163>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49444": {
+      "content": "<action_164>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49445": {
+      "content": "<action_165>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49446": {
+      "content": "<action_166>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49447": {
+      "content": "<action_167>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49448": {
+      "content": "<action_168>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49449": {
+      "content": "<action_169>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49450": {
+      "content": "<action_170>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49451": {
+      "content": "<action_171>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49452": {
+      "content": "<action_172>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49453": {
+      "content": "<action_173>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49454": {
+      "content": "<action_174>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49455": {
+      "content": "<action_175>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49456": {
+      "content": "<action_176>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49457": {
+      "content": "<action_177>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49458": {
+      "content": "<action_178>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49459": {
+      "content": "<action_179>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49460": {
+      "content": "<action_180>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49461": {
+      "content": "<action_181>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49462": {
+      "content": "<action_182>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49463": {
+      "content": "<action_183>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49464": {
+      "content": "<action_184>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49465": {
+      "content": "<action_185>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49466": {
+      "content": "<action_186>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49467": {
+      "content": "<action_187>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49468": {
+      "content": "<action_188>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49469": {
+      "content": "<action_189>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49470": {
+      "content": "<action_190>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49471": {
+      "content": "<action_191>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49472": {
+      "content": "<action_192>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49473": {
+      "content": "<action_193>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49474": {
+      "content": "<action_194>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49475": {
+      "content": "<action_195>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49476": {
+      "content": "<action_196>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49477": {
+      "content": "<action_197>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49478": {
+      "content": "<action_198>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49479": {
+      "content": "<action_199>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49480": {
+      "content": "<action_200>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49481": {
+      "content": "<action_201>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49482": {
+      "content": "<action_202>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49483": {
+      "content": "<action_203>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49484": {
+      "content": "<action_204>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49485": {
+      "content": "<action_205>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49486": {
+      "content": "<action_206>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49487": {
+      "content": "<action_207>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49488": {
+      "content": "<action_208>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49489": {
+      "content": "<action_209>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49490": {
+      "content": "<action_210>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49491": {
+      "content": "<action_211>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49492": {
+      "content": "<action_212>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49493": {
+      "content": "<action_213>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49494": {
+      "content": "<action_214>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49495": {
+      "content": "<action_215>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49496": {
+      "content": "<action_216>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49497": {
+      "content": "<action_217>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49498": {
+      "content": "<action_218>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49499": {
+      "content": "<action_219>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49500": {
+      "content": "<action_220>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49501": {
+      "content": "<action_221>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49502": {
+      "content": "<action_222>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49503": {
+      "content": "<action_223>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49504": {
+      "content": "<action_224>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49505": {
+      "content": "<action_225>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49506": {
+      "content": "<action_226>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49507": {
+      "content": "<action_227>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49508": {
+      "content": "<action_228>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49509": {
+      "content": "<action_229>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49510": {
+      "content": "<action_230>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49511": {
+      "content": "<action_231>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49512": {
+      "content": "<action_232>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49513": {
+      "content": "<action_233>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49514": {
+      "content": "<action_234>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49515": {
+      "content": "<action_235>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49516": {
+      "content": "<action_236>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49517": {
+      "content": "<action_237>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49518": {
+      "content": "<action_238>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49519": {
+      "content": "<action_239>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49520": {
+      "content": "<action_240>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49521": {
+      "content": "<action_241>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49522": {
+      "content": "<action_242>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49523": {
+      "content": "<action_243>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49524": {
+      "content": "<action_244>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49525": {
+      "content": "<action_245>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49526": {
+      "content": "<action_246>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49527": {
+      "content": "<action_247>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49528": {
+      "content": "<action_248>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49529": {
+      "content": "<action_249>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49530": {
+      "content": "<action_250>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49531": {
+      "content": "<action_251>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49532": {
+      "content": "<action_252>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49533": {
+      "content": "<action_253>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49534": {
+      "content": "<action_254>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49535": {
+      "content": "<action_255>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<action_250>",
+    "<action_251>",
+    "<action_252>",
+    "<action_253>",
+    "<action_254>",
+    "<action_255>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "end_of_utterance_token": "<end_of_utterance>",
+  "eos_token": "<end_of_utterance>",
+  "extra_special_tokens": {
+    "end_of_utterance_token": "<end_of_utterance>",
+    "fake_image_token": "<fake_token_around_image>",
+    "global_image_token": "<global-img>",
+    "image_token": "<image>"
+  },
+  "fake_image_token": "<fake_token_around_image>",
+  "global_image_token": "<global-img>",
+  "image_token": "<image>",
+  "legacy": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "processor_class": "SmolVLMProcessor",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

README.md

@@ -0,0 +1,269 @@
+---
+library_name: transformers
+license: apache-2.0
+datasets:
+- HuggingFaceM4/the_cauldron
+- HuggingFaceM4/Docmatix
+- lmms-lab/LLaVA-OneVision-Data
+- lmms-lab/M4-Instruct-Data
+- HuggingFaceFV/finevideo
+- MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
+- lmms-lab/LLaVA-Video-178K
+- orrzohar/Video-STaR
+- Mutonix/Vript
+- TIGER-Lab/VISTA-400K
+- Enxin/MovieChat-1K_train
+- ShareGPT4Video/ShareGPT4Video
+pipeline_tag: image-text-to-text
+language:
+- en
+base_model:
+- HuggingFaceTB/SmolVLM-256M-Instruct
+---
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM2_banner.png" width="800" height="auto" alt="Image description">
+
+# SmolVLM2-256M-Video
+
+SmolVLM2-256M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.38GB of GPU RAM for video inference. This efficiency makes it particularly well-suited for on-device applications that require specific domain fine-tuning and computational resources may be limited.
+## Model Summary
+
+- **Developed by:** Hugging Face 🤗
+- **Model type:** Multi-modal model (image/multi-image/video/text)
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
+
+## Resources
+
+- **Demo:** [Video Highlight Generator](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM2-HighlightGenerator)
+- **Blog:** [Blog post](https://huggingface.co/blog/smolvlm2)
+
+## Uses
+
+SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input consists of text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation.
+
+To fine-tune SmolVLM2 on a specific task, you can follow [the fine-tuning tutorial](https://github.com/huggingface/smollm/blob/main/vision/finetuning/Smol_VLM_FT.ipynb).
+
+## Evaluation 
+
+We evaluated the performance of the SmolVLM2 family on the following scientific benchmarks:
+
+| Size    | Video-MME | MLVU | MVBench |
+|----------|-----------------|----------|---------------|
+| 2.2B   | 52.1            | 55.2     | 46.27        |
+| 500M | 42.2            | 47.3     | 39.73        |
+| 256M | 33.7            | 40.6     | 32.7          |
+
+
+### How to get started
+
+You can use transformers to load, infer and fine-tune SmolVLM. Make sure you have num2words, flash-attn and latest transformers installed.
+You can load the model as follows.
+
+```python
+from transformers import AutoProcessor, AutoModelForImageTextToText
+import torch
+
+model_path = "HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
+processor = AutoProcessor.from_pretrained(model_path)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_path,
+    torch_dtype=torch.bfloat16,
+    _attn_implementation="flash_attention_2"
+).to("cuda")
+```
+
+#### Simple Inference
+
+You preprocess your inputs directly using chat templates and directly passing them 
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+            {"type": "text", "text": "Can you describe this image?"},            
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+print(generated_texts[0])
+```
+
+#### Video Inference
+
+To use SmolVLM2 for video inference, make sure you have decord installed. 
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "video", "path": "path_to_video.mp4"},
+            {"type": "text", "text": "Describe this video in detail"}
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+
+print(generated_texts[0])
+```
+#### Multi-image Interleaved Inference
+
+You can interleave multiple media with text using chat templates.
+
+```python
+import torch
+
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+          {"type": "text", "text": "What is the similarity between these two images?"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"},            
+        ]
+    },
+]
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+print(generated_texts[0])
+```
+
+
+### Model optimizations
+
+## Misuse and Out-of-scope Use
+
+SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
+
+- Prohibited Uses:
+  - Evaluating or scoring individuals (e.g., in employment, education, credit)
+  - Critical automated decision-making
+  - Generating unreliable factual content
+- Malicious Activities:
+  - Spam generation
+  - Disinformation campaigns
+  - Harassment or abuse
+  - Unauthorized surveillance
+
+### License
+
+SmolVLM2 is built upon [SigLIP](https://huggingface.co/google/siglip-base-patch16-512) as image encoder and [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) for text decoder part.
+
+We release the SmolVLM2 checkpoints under the Apache 2.0 license.
+
+## Citation information
+You can cite us in the following way:
+```bibtex
+@article{marafioti2025smolvlm,
+  title={SmolVLM: Redefining small and efficient multimodal models}, 
+  author={Andrés Marafioti and Orr Zohar and Miquel Farré and Merve Noyan and Elie Bakouch and Pedro Cuenca and Cyril Zakka and Loubna Ben Allal and Anton Lozhkov and Nouamane Tazi and Vaibhav Srivastav and Joshua Lochner and Hugo Larcher and Mathieu Morlon and Lewis Tunstall and Leandro von Werra and Thomas Wolf},
+  journal={arXiv preprint arXiv:2504.05299},
+  year={2025}
+}
+```
+
+## Training Data
+SmolVLM2 used 3.3M samples for training originally from ten different datasets: [LlaVa Onevision](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), [M4-Instruct](https://huggingface.co/datasets/lmms-lab/M4-Instruct-Data), [Mammoth](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M), [LlaVa Video 178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K), [FineVideo](https://huggingface.co/datasets/HuggingFaceFV/finevideo), [VideoStar](https://huggingface.co/datasets/orrzohar/Video-STaR), [VRipt](https://huggingface.co/datasets/Mutonix/Vript), [Vista-400K](https://huggingface.co/datasets/TIGER-Lab/VISTA-400K), [MovieChat](https://huggingface.co/datasets/Enxin/MovieChat-1K_train) and [ShareGPT4Video](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video).
+In the following plots we give a general overview of the samples across modalities and the source of those samples.
+<!--
+<center><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_data_split.png" width="auto" height="auto" alt="Image description">
+</center>
+
+### Details
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_datadetails.png" width="auto" height="auto" alt="Image description"> -->
+
+## Data Split per modality
+
+| Data Type    | Percentage |
+|--------------|------------|
+| Image        | 34.4%      |
+| Text         | 20.2%      |
+| Video        | 33.0%      |
+| Multi-image  | 12.3%      |
+
+
+## Granular dataset slices per modality
+
+### Text Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-onevision/magpie_pro_ft3_80b_mt      | 6.8%       |
+| llava-onevision/magpie_pro_ft3_80b_tt      | 6.8%       |
+| llava-onevision/magpie_pro_qwen2_72b_tt    | 5.8%       |
+| llava-onevision/mathqa                     | 0.9%       |
+
+### Multi-image Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| m4-instruct-data/m4_instruct_multiimage    | 10.4%      |
+| mammoth/multiimage-cap6                    | 1.9%       |
+
+### Image Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-onevision/other                      | 17.4%      |
+| llava-onevision/vision_flan                | 3.9%       |
+| llava-onevision/mavis_math_metagen         | 2.6%       |
+| llava-onevision/mavis_math_rule_geo        | 2.5%       |
+| llava-onevision/sharegpt4o                 | 1.7%       |
+| llava-onevision/sharegpt4v_coco            | 1.5%       |
+| llava-onevision/image_textualization       | 1.3%       |
+| llava-onevision/sharegpt4v_llava           | 0.9%       |
+| llava-onevision/mapqa                      | 0.9%       |
+| llava-onevision/qa                         | 0.8%       |
+| llava-onevision/textocr                    | 0.8%       |
+
+### Video Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-video-178k/1-2m                      | 7.3%       |
+| llava-video-178k/2-3m                      | 7.0%       |
+| other-video/combined                       | 5.7%       |
+| llava-video-178k/hound                     | 4.4%       |
+| llava-video-178k/0-30s                     | 2.4%       |
+| video-star/starb                           | 2.2%       |
+| vista-400k/combined                        | 2.2%       |
+| vript/long                                 | 1.0%       |
+| ShareGPT4Video/all                         | 0.8%       |

SmolVLM2-500M-Video-Instruct-Action/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

SmolVLM2-500M-Video-Instruct-Action/README.md

@@ -0,0 +1,270 @@
+---
+library_name: transformers
+license: apache-2.0
+datasets:
+- HuggingFaceM4/the_cauldron
+- HuggingFaceM4/Docmatix
+- lmms-lab/LLaVA-OneVision-Data
+- lmms-lab/M4-Instruct-Data
+- HuggingFaceFV/finevideo
+- MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
+- lmms-lab/LLaVA-Video-178K
+- orrzohar/Video-STaR
+- Mutonix/Vript
+- TIGER-Lab/VISTA-400K
+- Enxin/MovieChat-1K_train
+- ShareGPT4Video/ShareGPT4Video
+pipeline_tag: image-text-to-text
+language:
+- en
+base_model:
+- HuggingFaceTB/SmolVLM-500M-Instruct
+---
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM2_banner.png" width="800" height="auto" alt="Image description">
+
+# SmolVLM2-500M-Video
+
+SmolVLM2-500M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.8GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks. This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited.
+## Model Summary
+
+- **Developed by:** Hugging Face 🤗
+- **Model type:** Multi-modal model (image/multi-image/video/text)
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary)
+
+## Resources
+
+- **Demo:** [Video Highlight Generator](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM2-HighlightGenerator)
+- **Blog:** [Blog post](https://huggingface.co/blog/smolvlm2)
+
+## Uses
+
+SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input consists of text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation.
+
+To fine-tune SmolVLM2 on a specific task, you can follow [the fine-tuning tutorial](https://github.com/huggingface/smollm/blob/main/vision/finetuning/Smol_VLM_FT.ipynb).
+
+## Evaluation 
+
+We evaluated the performance of the SmolVLM2 family on the following scientific benchmarks:
+
+| Size    | Video-MME | MLVU | MVBench |
+|----------|-----------------|----------|---------------|
+| 2.2B   | 52.1            | 55.2     | 46.27        |
+| 500M | 42.2            | 47.3     | 39.73        |
+| 256M | 33.7            | 40.6     | 32.7          |
+
+
+### How to get started
+
+You can use transformers to load, infer and fine-tune SmolVLM. Make sure you have num2words, flash-attn and latest transformers installed.
+You can load the model as follows.
+
+```python
+from transformers import AutoProcessor, AutoModelForImageTextToText
+import torch
+
+model_path = "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
+processor = AutoProcessor.from_pretrained(model_path)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_path,
+    torch_dtype=torch.bfloat16,
+    _attn_implementation="flash_attention_2"
+).to("cuda")
+```
+
+#### Simple Inference
+
+You preprocess your inputs directly using chat templates and directly passing them 
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+            {"type": "text", "text": "Can you describe this image?"},
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+print(generated_texts[0])
+```
+
+#### Video Inference
+
+To use SmolVLM2 for video inference, make sure you have decord installed. 
+
+```python
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "video", "path": "path_to_video.mp4"},
+            {"type": "text", "text": "Describe this video in detail"}
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+
+print(generated_texts[0])
+```
+#### Multi-image Interleaved Inference
+
+You can interleave multiple media with text using chat templates.
+
+```python
+import torch
+
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+          {"type": "text", "text": "What is the similarity between these two images?"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"},            
+        ]
+    },
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
+
+generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+print(generated_texts[0])
+```
+
+
+### Model optimizations
+
+## Misuse and Out-of-scope Use
+
+SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
+
+- Prohibited Uses:
+  - Evaluating or scoring individuals (e.g., in employment, education, credit)
+  - Critical automated decision-making
+  - Generating unreliable factual content
+- Malicious Activities:
+  - Spam generation
+  - Disinformation campaigns
+  - Harassment or abuse
+  - Unauthorized surveillance
+
+### License
+
+SmolVLM2 is built upon [SigLIP](https://huggingface.co/google/siglip-base-patch16-512) as image encoder and [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) for text decoder part.
+
+We release the SmolVLM2 checkpoints under the Apache 2.0 license.
+
+## Citation information
+You can cite us in the following way:
+```bibtex
+@article{marafioti2025smolvlm,
+  title={SmolVLM: Redefining small and efficient multimodal models}, 
+  author={Andrés Marafioti and Orr Zohar and Miquel Farré and Merve Noyan and Elie Bakouch and Pedro Cuenca and Cyril Zakka and Loubna Ben Allal and Anton Lozhkov and Nouamane Tazi and Vaibhav Srivastav and Joshua Lochner and Hugo Larcher and Mathieu Morlon and Lewis Tunstall and Leandro von Werra and Thomas Wolf},
+  journal={arXiv preprint arXiv:2504.05299},
+  year={2025}
+}
+```
+
+## Training Data
+SmolVLM2 used 3.3M samples for training originally from ten different datasets: [LlaVa Onevision](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), [M4-Instruct](https://huggingface.co/datasets/lmms-lab/M4-Instruct-Data), [Mammoth](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M), [LlaVa Video 178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K), [FineVideo](https://huggingface.co/datasets/HuggingFaceFV/finevideo), [VideoStar](https://huggingface.co/datasets/orrzohar/Video-STaR), [VRipt](https://huggingface.co/datasets/Mutonix/Vript), [Vista-400K](https://huggingface.co/datasets/TIGER-Lab/VISTA-400K), [MovieChat](https://huggingface.co/datasets/Enxin/MovieChat-1K_train) and [ShareGPT4Video](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video).
+In the following plots we give a general overview of the samples across modalities and the source of those samples.
+<!--
+<center><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_data_split.png" width="auto" height="auto" alt="Image description">
+</center>
+
+### Details
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm2_datadetails.png" width="auto" height="auto" alt="Image description"> -->
+
+## Data Split per modality
+
+| Data Type    | Percentage |
+|--------------|------------|
+| Image        | 34.4%      |
+| Text         | 20.2%      |
+| Video        | 33.0%      |
+| Multi-image  | 12.3%      |
+
+
+## Granular dataset slices per modality
+
+### Text Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-onevision/magpie_pro_ft3_80b_mt      | 6.8%       |
+| llava-onevision/magpie_pro_ft3_80b_tt      | 6.8%       |
+| llava-onevision/magpie_pro_qwen2_72b_tt    | 5.8%       |
+| llava-onevision/mathqa                     | 0.9%       |
+
+### Multi-image Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| m4-instruct-data/m4_instruct_multiimage    | 10.4%      |
+| mammoth/multiimage-cap6                    | 1.9%       |
+
+### Image Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-onevision/other                      | 17.4%      |
+| llava-onevision/vision_flan                | 3.9%       |
+| llava-onevision/mavis_math_metagen         | 2.6%       |
+| llava-onevision/mavis_math_rule_geo        | 2.5%       |
+| llava-onevision/sharegpt4o                 | 1.7%       |
+| llava-onevision/sharegpt4v_coco            | 1.5%       |
+| llava-onevision/image_textualization       | 1.3%       |
+| llava-onevision/sharegpt4v_llava           | 0.9%       |
+| llava-onevision/mapqa                      | 0.9%       |
+| llava-onevision/qa                         | 0.8%       |
+| llava-onevision/textocr                    | 0.8%       |
+
+### Video Datasets
+| Dataset                                    | Percentage |
+|--------------------------------------------|------------|
+| llava-video-178k/1-2m                      | 7.3%       |
+| llava-video-178k/2-3m                      | 7.0%       |
+| other-video/combined                       | 5.7%       |
+| llava-video-178k/hound                     | 4.4%       |
+| llava-video-178k/0-30s                     | 2.4%       |
+| video-star/starb                           | 2.2%       |
+| vista-400k/combined                        | 2.2%       |
+| vript/long                                 | 1.0%       |
+| ShareGPT4Video/all                         | 0.8%       |

SmolVLM2-500M-Video-Instruct-Action/added_tokens.json

@@ -0,0 +1,131 @@
+{
+  "<action>": 49280,
+  "<end_of_utterance>": 49279,
+  "<fake_token_around_image>": 49189,
+  "<global-img>": 49152,
+  "<image>": 49190,
+  "<row_1_col_1>": 49153,
+  "<row_1_col_2>": 49154,
+  "<row_1_col_3>": 49155,
+  "<row_1_col_4>": 49156,
+  "<row_1_col_5>": 49157,
+  "<row_1_col_6>": 49158,
+  "<row_2_col_1>": 49159,
+  "<row_2_col_2>": 49160,
+  "<row_2_col_3>": 49161,
+  "<row_2_col_4>": 49162,
+  "<row_2_col_5>": 49163,
+  "<row_2_col_6>": 49164,
+  "<row_3_col_1>": 49165,
+  "<row_3_col_2>": 49166,
+  "<row_3_col_3>": 49167,
+  "<row_3_col_4>": 49168,
+  "<row_3_col_5>": 49169,
+  "<row_3_col_6>": 49170,
+  "<row_4_col_1>": 49171,
+  "<row_4_col_2>": 49172,
+  "<row_4_col_3>": 49173,
+  "<row_4_col_4>": 49174,
+  "<row_4_col_5>": 49175,
+  "<row_4_col_6>": 49176,
+  "<row_5_col_1>": 49177,
+  "<row_5_col_2>": 49178,
+  "<row_5_col_3>": 49179,
+  "<row_5_col_4>": 49180,
+  "<row_5_col_5>": 49181,
+  "<row_5_col_6>": 49182,
+  "<row_6_col_1>": 49183,
+  "<row_6_col_2>": 49184,
+  "<row_6_col_3>": 49185,
+  "<row_6_col_4>": 49186,
+  "<row_6_col_5>": 49187,
+  "<row_6_col_6>": 49188,
+  "<|reserved_special_token_0|>": 49191,
+  "<|reserved_special_token_10|>": 49201,
+  "<|reserved_special_token_11|>": 49202,
+  "<|reserved_special_token_12|>": 49203,
+  "<|reserved_special_token_13|>": 49204,
+  "<|reserved_special_token_14|>": 49205,
+  "<|reserved_special_token_15|>": 49206,
+  "<|reserved_special_token_16|>": 49207,
+  "<|reserved_special_token_17|>": 49208,
+  "<|reserved_special_token_18|>": 49209,
+  "<|reserved_special_token_19|>": 49210,
+  "<|reserved_special_token_1|>": 49192,
+  "<|reserved_special_token_20|>": 49211,
+  "<|reserved_special_token_21|>": 49212,
+  "<|reserved_special_token_22|>": 49213,
+  "<|reserved_special_token_23|>": 49214,
+  "<|reserved_special_token_24|>": 49215,
+  "<|reserved_special_token_25|>": 49216,
+  "<|reserved_special_token_26|>": 49217,
+  "<|reserved_special_token_27|>": 49218,
+  "<|reserved_special_token_28|>": 49219,
+  "<|reserved_special_token_29|>": 49220,
+  "<|reserved_special_token_2|>": 49193,
+  "<|reserved_special_token_30|>": 49221,
+  "<|reserved_special_token_31|>": 49222,
+  "<|reserved_special_token_32|>": 49223,
+  "<|reserved_special_token_33|>": 49224,
+  "<|reserved_special_token_34|>": 49225,
+  "<|reserved_special_token_35|>": 49226,
+  "<|reserved_special_token_36|>": 49227,
+  "<|reserved_special_token_37|>": 49228,
+  "<|reserved_special_token_38|>": 49229,
+  "<|reserved_special_token_39|>": 49230,
+  "<|reserved_special_token_3|>": 49194,
+  "<|reserved_special_token_40|>": 49231,
+  "<|reserved_special_token_41|>": 49232,
+  "<|reserved_special_token_42|>": 49233,
+  "<|reserved_special_token_43|>": 49234,
+  "<|reserved_special_token_44|>": 49235,
+  "<|reserved_special_token_45|>": 49236,
+  "<|reserved_special_token_46|>": 49237,
+  "<|reserved_special_token_47|>": 49238,
+  "<|reserved_special_token_48|>": 49239,
+  "<|reserved_special_token_49|>": 49240,
+  "<|reserved_special_token_4|>": 49195,
+  "<|reserved_special_token_50|>": 49241,
+  "<|reserved_special_token_51|>": 49242,
+  "<|reserved_special_token_52|>": 49243,
+  "<|reserved_special_token_53|>": 49244,
+  "<|reserved_special_token_54|>": 49245,
+  "<|reserved_special_token_55|>": 49246,
+  "<|reserved_special_token_56|>": 49247,
+  "<|reserved_special_token_57|>": 49248,
+  "<|reserved_special_token_58|>": 49249,
+  "<|reserved_special_token_59|>": 49250,
+  "<|reserved_special_token_5|>": 49196,
+  "<|reserved_special_token_60|>": 49251,
+  "<|reserved_special_token_61|>": 49252,
+  "<|reserved_special_token_62|>": 49253,
+  "<|reserved_special_token_63|>": 49254,
+  "<|reserved_special_token_64|>": 49255,
+  "<|reserved_special_token_65|>": 49256,
+  "<|reserved_special_token_66|>": 49257,
+  "<|reserved_special_token_67|>": 49258,
+  "<|reserved_special_token_68|>": 49259,
+  "<|reserved_special_token_69|>": 49260,
+  "<|reserved_special_token_6|>": 49197,
+  "<|reserved_special_token_70|>": 49261,
+  "<|reserved_special_token_71|>": 49262,
+  "<|reserved_special_token_72|>": 49263,
+  "<|reserved_special_token_73|>": 49264,
+  "<|reserved_special_token_74|>": 49265,
+  "<|reserved_special_token_75|>": 49266,
+  "<|reserved_special_token_76|>": 49267,
+  "<|reserved_special_token_77|>": 49268,
+  "<|reserved_special_token_78|>": 49269,
+  "<|reserved_special_token_79|>": 49270,
+  "<|reserved_special_token_7|>": 49198,
+  "<|reserved_special_token_80|>": 49271,
+  "<|reserved_special_token_81|>": 49272,
+  "<|reserved_special_token_82|>": 49273,
+  "<|reserved_special_token_83|>": 49274,
+  "<|reserved_special_token_84|>": 49275,
+  "<|reserved_special_token_85|>": 49276,
+  "<|reserved_special_token_86|>": 49277,
+  "<|reserved_special_token_87|>": 49278,
+  "<|reserved_special_token_8|>": 49199,
+  "<|reserved_special_token_9|>": 49200
+}

SmolVLM2-500M-Video-Instruct-Action/chat_template.jinja

@@ -0,0 +1,2 @@
+<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
+{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}

SmolVLM2-500M-Video-Instruct-Action/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}"
+}

SmolVLM2-500M-Video-Instruct-Action/config.json

@@ -0,0 +1,157 @@
+{
+  "architectures": [
+    "SmolVLMForConditionalGeneration"
+  ],
+  "image_token_id": 49190,
+  "model_type": "smolvlm",
+  "pad_token_id": 128002,
+  "scale_factor": 4,
+  "text_config": {
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 960,
+    "initializer_range": 0.02,
+    "intermediate_size": 2560,
+    "is_llama_config": true,
+    "max_position_embeddings": 8192,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_attention_heads": 15,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 5,
+    "pad_token_id": 2,
+    "perceiver_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "vllama3",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_key_value_heads": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "qk_layer_norms_perceiver": false,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resampler_depth": 6,
+      "resampler_head_dim": 96,
+      "resampler_n_heads": 16,
+      "resampler_n_latents": 64,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.46.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "pixel_shuffle_factor": 4,
+    "pretraining_tp": 1,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_interleaved": false,
+    "rope_scaling": null,
+    "rope_theta": 100000,
+    "torch_dtype": "float32",
+    "transformers.js_config": {
+      "kv_cache_dtype": {
+        "fp16": "float16",
+        "q4f16": "float16"
+      }
+    },
+    "use_cache": true,
+    "use_resampler": false,
+    "vocab_size": 49281
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_reentrant_checkpointing": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_image_size": {
+      "longest_edge": 512
+    },
+    "model_type": "smolvlm_vision",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "size": {
+      "longest_edge": 512
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "use_base_siglip": false
+  },
+  "vocab_size": 49281,
+  "action_dim": 7
+}

SmolVLM2-500M-Video-Instruct-Action/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 49279,
+  "pad_token_id": 2,
+  "transformers_version": "4.52.4"
+}

SmolVLM2-500M-Video-Instruct-Action/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ab8a3f316e950c0f5eba355fe24b65f69096a112d8fd9b7f49133a16e65b08
+size 2029998304

SmolVLM2-500M-Video-Instruct-Action/onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8743f020606f401ffa0c0ec7a7055da6ad7518b981ecdb060b62da3a60ec45
+size 1450426001