xrenaa commited on
Commit
701db92
·
verified ·
1 Parent(s): 216a537

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. Cosmos-Guardrail1/.gitattributes +42 -0
  3. Cosmos-Guardrail1/README.md +244 -0
  4. Cosmos-Guardrail1/blocklist/custom/blocklist +383 -0
  5. Cosmos-Guardrail1/blocklist/exact_match/blocked +1414 -0
  6. Cosmos-Guardrail1/blocklist/nltk_data/corpora/wordnet.zip +3 -0
  7. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab.zip +3 -0
  8. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/README +98 -0
  9. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/abbrev_types.txt +118 -0
  10. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/collocations.tab +96 -0
  11. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/ortho_context.tab +0 -0
  12. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/sent_starters.txt +54 -0
  13. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/abbrev_types.txt +211 -0
  14. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/collocations.tab +101 -0
  15. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/ortho_context.tab +0 -0
  16. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/sent_starters.txt +64 -0
  17. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/abbrev_types.txt +99 -0
  18. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/collocations.tab +37 -0
  19. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/ortho_context.tab +0 -0
  20. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/sent_starters.txt +54 -0
  21. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txt +156 -0
  22. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/collocations.tab +37 -0
  23. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/ortho_context.tab +0 -0
  24. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/sent_starters.txt +39 -0
  25. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/abbrev_types.txt +48 -0
  26. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/collocations.tab +100 -0
  27. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/ortho_context.tab +0 -0
  28. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/sent_starters.txt +89 -0
  29. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/abbrev_types.txt +81 -0
  30. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/collocations.tab +167 -0
  31. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/ortho_context.tab +0 -0
  32. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/sent_starters.txt +86 -0
  33. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/abbrev_types.txt +61 -0
  34. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/collocations.tab +18 -0
  35. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/ortho_context.tab +0 -0
  36. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/sent_starters.txt +48 -0
  37. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/abbrev_types.txt +71 -0
  38. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/collocations.tab +28 -0
  39. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/ortho_context.tab +0 -0
  40. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/sent_starters.txt +107 -0
  41. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/abbrev_types.txt +100 -0
  42. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/collocations.tab +7 -0
  43. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/ortho_context.tab +0 -0
  44. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/sent_starters.txt +54 -0
  45. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/abbrev_types.txt +125 -0
  46. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/collocations.tab +6 -0
  47. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/ortho_context.tab +0 -0
  48. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/sent_starters.txt +40 -0
  49. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/norwegian/abbrev_types.txt +106 -0
  50. Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/norwegian/collocations.tab +54 -0
.gitattributes CHANGED
@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ Cosmos-Guardrail1/video_content_safety_filter/models--google--siglip-so400m-patch14-384/blobs/1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec filter=lfs diff=lfs merge=lfs -text
38
+ Cosmos-Guardrail1/video_content_safety_filter/models--google--siglip-so400m-patch14-384/blobs/ea2abad2b7f8a9c1aa5e49a244d5d57ffa71c56f720c94bc5d240ef4d6e1d94a filter=lfs diff=lfs merge=lfs -text
Cosmos-Guardrail1/.gitattributes ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ aegis/models--meta-llama--LlamaGuard-7b/blobs/4d92c8b74f78b0e0f4b32921d13a007efcd0e0447290da6d92f787c3295b0ad8 filter=lfs diff=lfs merge=lfs -text
37
+ aegis/models--meta-llama--LlamaGuard-7b/blobs/9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 filter=lfs diff=lfs merge=lfs -text
38
+ aegis/models--meta-llama--LlamaGuard-7b/blobs/a19b92a679870c311122d67ae980737cf3e51424b396b3809463c4d9b06c7fcf filter=lfs diff=lfs merge=lfs -text
39
+ aegis/models--meta-llama--LlamaGuard-7b/blobs/f9e6f2ab03a3b92bf4bc6cfd6d6dcdaa8b36ab5ecf73dcfd1e8da3b5a95261a8 filter=lfs diff=lfs merge=lfs -text
40
+ aegis/models--nvidia--Aegis-AI-Content-Safety-LlamaGuard-Defensive-1.0/blobs/d79b29a0b9ab36db8038e39e847b3c81ebd56dd8d796551943ea4b43b2e6c55c filter=lfs diff=lfs merge=lfs -text
41
+ video_content_safety_filter/models--google--siglip-so400m-patch14-384/blobs/1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec filter=lfs diff=lfs merge=lfs -text
42
+ video_content_safety_filter/models--google--siglip-so400m-patch14-384/blobs/ea2abad2b7f8a9c1aa5e49a244d5d57ffa71c56f720c94bc5d240ef4d6e1d94a filter=lfs diff=lfs merge=lfs -text
Cosmos-Guardrail1/README.md ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: nvidia-open-model-license
4
+ license_link: >-
5
+ https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license
6
+ library_name: cosmos
7
+ tags:
8
+ - nvidia
9
+ - cosmos
10
+ extra_gated_prompt: >-
11
+ # NVIDIA Open Model License Agreement
12
+
13
+ Version Release Date: January 6, 2025
14
+
15
+ This NVIDIA Open Model License Agreement (the "<ins>Agreement</ins>") is a legal agreement between the Legal Entity You represent, or if no entity is identified, You and NVIDIA Corporation and its Affiliates ("<ins>NVIDIA</ins>") and governs Your use of the Models that NVIDIA provides to You under this Agreement. NVIDIA and You are each a "<ins>party</ins>" and collectively the "<ins>parties</ins>."
16
+
17
+ NVIDIA models released under this Agreement are intended to be used permissively and enable the further development of AI technologies. Subject to the terms of this Agreement, NVIDIA confirms that:
18
+
19
+ * Models are commercially usable.
20
+
21
+ * You are free to create and distribute Derivative Models.
22
+
23
+ * NVIDIA does not claim ownership to any outputs generated using the Models or Model Derivatives.
24
+
25
+ By using, reproducing, modifying, distributing, performing or displaying any portion or element of the Model or Derivative Model, or otherwise accepting the terms of this Agreement, you agree to be bound by this Agreement.
26
+
27
+ ## 1. Definitions
28
+
29
+ The following definitions apply to this Agreement:
30
+
31
+ 1.1. "<ins>NVIDIA Cosmos Model</ins>" means a multimodal Model shared under this Agreement.
32
+
33
+ 1.2. "<ins>Derivative Model</ins>" means all (a) modifications to the Model, (b) works based on the Model, and (c) any other derivative works of the Model. An output is not a Derivative Model.
34
+
35
+ 1.3. "<ins>Legal Entity</ins>" means the union of the acting entity and all other entities that <ins>control</ins>, are controlled by, or are under common control with that entity. For the purposes of this definition, "<ins>control</ins>" means (a) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (b) ownership of fifty percent (50%) or more of the outstanding shares, or (c) beneficial ownership of such entity.
36
+
37
+ 1.4. "<ins>Model</ins>" means the machine learning model, software, checkpoints, learnt weights, algorithms, parameters, configuration files and documentation shared under this Agreement.
38
+
39
+ 1.5. "<ins>You</ins>" or "<ins>Your</ins>" means an individual or Legal Entity exercising permissions granted by this Agreement.
40
+
41
+ ## 2. Conditions for Use, License Grant, AI Ethics and IP Ownership
42
+
43
+ 2.1. Conditions for Use. The Model and any Derivative Model are subject to additional terms as described in Section 2 and Section 3 of this Agreement and govern Your use. If You institute copyright or patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Model or a Derivative Model constitutes direct or contributory copyright or patent infringement, then any licenses granted to You under this Agreement for that Model or Derivative Model will terminate as of the date such litigation is filed. If You bypass, disable, reduce the efficacy of, or circumvent any technical limitation, safety guardrail or associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism contained in the Model, your rights under this Agreement will automatically terminate. NVIDIA may update this Agreement to comply with legal and regulatory requirements at any time and You agree to either comply with any updated license or cease Your copying, use, and distribution of the Model and any Derivative Model.
44
+
45
+ 2.2. License Grant. The rights granted herein are explicitly conditioned on Your full compliance with the terms of this Agreement. Subject to the terms and conditions of this Agreement, NVIDIA hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, revocable (as stated in Section 2.1) license to publicly perform, publicly display, reproduce, use, create derivative works of, make, have made, sell, offer for sale, distribute (through multiple tiers of distribution) and import the Model.
46
+
47
+ 2.3. AI Ethics. Use of the Models under the Agreement must be consistent with NVIDIA's Trustworthy AI terms found at https://www.nvidia.com/en-us/agreements/trustworthy-ai/terms/.
48
+
49
+ 2.4. NVIDIA owns the Model and any Model Derivatives created by NVIDIA. Subject to NVIDIA's underlying ownership rights in the Model or its Model Derivatives, You are and will be the owner of Your Model Derivatives. NVIDIA claims no ownership rights in outputs. You are responsible for outputs and their subsequent uses. Except as expressly granted in this Agreement, (a) NVIDIA reserves all rights, interests and remedies in connection with the Model and (b) no other license or right is granted to you by implication, estoppel or otherwise.
50
+
51
+ ## 3. Redistribution
52
+
53
+ You may reproduce and distribute copies of the Model or Derivative Models thereof in any medium, with or without modifications, provided that You meet the following conditions:
54
+
55
+ 3.1. If you distribute the Model, You must give any other recipients of the Model a copy of this Agreement and include the following attribution notice within a "Notice" text file with such copies: "Licensed by NVIDIA Corporation under the NVIDIA Open Model License";
56
+
57
+ 3.2. If you distribute or make available a NVIDIA Cosmos Model, or a product or service (including an AI model) that contains or uses a NVIDIA Cosmos Model, use a NVIDIA Cosmos Model to create a Derivative Model, or use a NVIDIA Cosmos Model or its outputs to create, train, fine tune, or otherwise improve an AI model, you will include "Built on NVIDIA Cosmos" on a related website, user interface, blogpost, about page, or product documentation; and
58
+
59
+ 3.3. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Models as a whole, provided Your use, reproduction, and distribution of the Model otherwise complies with the conditions stated in this Agreement.
60
+
61
+ ## 4. Trademarks
62
+
63
+ This Agreement does not grant permission to use the trade names, trademarks, service marks, or product names of NVIDIA, except as required for reasonable and customary use in describing the origin of the Model and reproducing the content of the "Notice" text file.
64
+
65
+ ## **5. Disclaimer of Warranty**
66
+
67
+ **Unless required by applicable law or agreed to in writing, NVIDIA provides the Model on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Model, Derivative Models and outputs and assume any risks associated with Your exercise of permissions under this Agreement.**
68
+
69
+ ## **6. Limitation of Liability**
70
+
71
+ **In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, will NVIDIA be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this Agreement or out of the use or inability to use the Model, Derivative Models or outputs (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if NVIDIA has been advised of the possibility of such damages.**
72
+
73
+ ## 7. Indemnity
74
+
75
+ You will indemnify and hold harmless NVIDIA from and against any claim by any third party arising out of or related to your use or distribution of the Model, Model Derivatives or outputs.
76
+
77
+ ## 8. Feedback
78
+
79
+ NVIDIA appreciates your feedback, and You agree that NVIDIA may use it without restriction or compensation to You.
80
+
81
+ ## 9. Governing Law
82
+
83
+ This Agreement will be governed in all respects by the laws of the United States and the laws of the State of Delaware, without regard to conflict of laws principles or the United Nations Convention on Contracts for the International Sale of Goods. The state and federal courts residing in Santa Clara County, California will have exclusive jurisdiction over any dispute or claim arising out of or related to this Agreement, and the parties irrevocably consent to personal jurisdiction and venue in those courts; except that, either party may apply for injunctive remedies or an equivalent type of urgent legal relief in any jurisdiction.
84
+
85
+ ## 10. Trade and Compliance
86
+
87
+ You agree to comply with all applicable export, import, trade and economic sanctions laws and regulations, as amended, including without limitation U.S. Export Administration Regulations and Office of Foreign Assets Control regulations. These laws include restrictions on destinations, end-users and end-use.
88
+ extra_gated_fields:
89
+ By clicking Submit below, I accept the terms of the NVIDIA Open Model License Agreement and acknowledge that I am an adult of legal age of majority in the country in which the Cosmos Models will be used and have authority to accept this Agreement: checkbox
90
+ extra_gated_description: >-
91
+ The information you provide will be collected, stored, processed and shared in accordance with the [NVIDIA Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/).
92
+ extra_gated_button_content: Submit
93
+ ---
94
+ # **Cosmos-Guardrail1**
95
+
96
+ [**Cosmos**](https://huggingface.co/collections/nvidia/cosmos-predict1-67c9d1b97678dbf7669c89a7) | [**Code**](https://github.com/nvidia-cosmos/cosmos-predict1) | [**Paper**](https://arxiv.org/abs/2501.03575) | [**Paper Website**](https://research.nvidia.com/labs/dir/cosmos-predict1)
97
+
98
+ # Model Overview
99
+
100
+ ## Description:
101
+ **Cosmos World Foundation Models**: A family of highly performant pre-trained world foundation models purpose-built for generating physics-aware videos and world states for physical AI development.
102
+
103
+ Cosmos Guardrail is a content safety model comprising of four components that enforce content safety. The components are as follows.
104
+
105
+ 1. Aegis-AI-Content-Safety-LlamaGuard-LLM-Defensive-1.0: An LLM fine-tuned for content safety. It is a parameter-efficient instruction-tuned version of Llama-Guard based on Llama2-7B, which is trained on NVIDIA's Aegis Content Safety Dataset covering NVIDIA's broad taxonomy of 13 critical safety risk categories. See model card [here](https://huggingface.co/nvidia/Aegis-AI-Content-Safety-LlamaGuard-Defensive-1.0).
106
+
107
+ 2. Blocklist: A set of human-curated keywords that are used to filter our corner-cases.
108
+
109
+ 3. Video Content Safety Filter: A multi-class classifier model that is trained to distinguish between safe and unsafe frames of the generated video using SigLIP embeddings [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384).
110
+
111
+ 4. Face Blur Filter: A pixelation filter that uses [RetinaFace](https://github.com/biubug6/Pytorch_Retinaface) to identify facial regions with high confidence scores and apply pixelation to any detections larger than 20x20 pixels.
112
+
113
+ **Model Developer**: NVIDIA
114
+
115
+ ## Model Versions
116
+
117
+ [Cosmos-Guardrail1](https://huggingface.co/nvidia/Cosmos-Guardrail1).
118
+
119
+ ## License:
120
+ This model is released under the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). For a custom license, please contact [cosmos-license@nvidia.com](mailto:cosmos-license@nvidia.com).
121
+
122
+ Under the NVIDIA Open Model License, NVIDIA confirms:
123
+
124
+ * Models are commercially usable.
125
+ * You are free to create and distribute Derivative Models.
126
+ * NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
127
+
128
+ **Important Note**: If you bypass, disable, reduce the efficacy of, or circumvent any technical limitation, safety guardrail or
129
+ associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism contained
130
+ in the Model, your rights under [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) will automatically terminate.
131
+
132
+ **Additional Information**: [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama2/LICENSE).
133
+
134
+ ## Model Architecture:
135
+
136
+ * **Aegis**: Llama 2 backbone
137
+ * **Video Content Safety Filter**: MLP backbone using SigLIP embeddings
138
+ * **Face Blur Filter**: ResNet-50 backbone
139
+
140
+ ## Input/Output Specifications
141
+
142
+ * **Input Type(s)**: Text, Video
143
+ * **Input Format(s)**:
144
+ * Text (str): Input prompt
145
+ * Video (np.ndarray): Video frames
146
+ * **Input Parameters**:
147
+ * Text: One-dimensional (1D)
148
+ * Video: Three-dimensional (3D)
149
+
150
+ ## Output:
151
+ * **Output Type(s):** Boolean, Text, Video <br>
152
+ * **Output Format(s)**:
153
+ * Boolean: True for safe and False for unsafe
154
+ * Text (str): Reason for the unsafe determination
155
+ * Video (np.ndarray): Processed video frames where faces are blurred
156
+ * **Output Parameters**:
157
+ * Boolean: One-dimensional (1D)
158
+ * Text: One-dimensional (1D)
159
+ * Video: Three-dimensional (3D)
160
+
161
+
162
+ ## Software Integration:
163
+ **Runtime Engine(s):**
164
+ * [Cosmos-Predict1](https://github.com/nvidia-cosmos/cosmos-predict1)
165
+ * [Cosmos-Transfer1](https://github.com/nvidia-cosmos/cosmos-transfer1)
166
+
167
+ **Supported Hardware Microarchitecture Compatibility:** <br>
168
+ * NVIDIA Ampere <br>
169
+ * NVIDIA Hopper <br>
170
+ **Supported Operating System(s):** Linux <br>
171
+
172
+ # Usage
173
+
174
+ On how to use the model, see:
175
+ * [Cosmos-Predict1](https://github.com/nvidia-cosmos/cosmos-predict1)
176
+ * [Cosmos-Transfer1](https://github.com/nvidia-cosmos/cosmos-transfer1)
177
+
178
+ Example for the prompt-checking portion of the Guardrail:
179
+
180
+ * Input: `"A dog is playing with a ball."`
181
+ * Output: Guardrail allows the generation of this video
182
+
183
+ * Input: `"A man wearing only socks."`
184
+ * Output: Guardrail blocks generation of this video
185
+
186
+ ## Ethical Considerations
187
+ NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
188
+
189
+ For more detailed information on ethical considerations for this model, please see the subcards of Explainability, Bias, Safety & Security, and Privacy below. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
190
+
191
+ ### Plus Plus (++) Promise
192
+
193
+ We value you, the datasets, the diversity they represent, and what we have been entrusted with. This model and its associated data have been:
194
+ * Verified to comply with current applicable disclosure laws, regulations, and industry standards.
195
+ * Verified to comply with applicable privacy labeling requirements.
196
+ * Annotated to describe the collector/source (NVIDIA or a third-party).
197
+ * Characterized for technical limitations.
198
+ * Reviewed to ensure proper disclosure is accessible to, maintained for, and in compliance with NVIDIA data subjects and their requests.
199
+ * Reviewed before release.
200
+ * Tagged for known restrictions and potential safety implications.
201
+
202
+ ### Bias
203
+
204
+ Field | Response
205
+ :---------------------------------------------------------------------------------------------------|:---------------
206
+ Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None
207
+ Measures taken to mitigate against unwanted bias: | None
208
+
209
+
210
+ ### Explainability
211
+
212
+ Field | Response
213
+ :------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
214
+ Intended Application & Domain: | Content moderation for world generation
215
+ Model Type: | Ensemble
216
+ Intended Users: | Generative AI developers for world generation models
217
+ Output: | Boolean
218
+ Describe how the model works: | Check safety of input prompts or generated videos and output a safety classification
219
+ Technical Limitations: | The model may not moderate input prompt accurately and may have incorrect responses.
220
+ Verified to have met prescribed NVIDIA quality standards: | Yes
221
+ Performance Metrics: | Human Evaluation
222
+ Potential Known Risks: | The model's output can potentially classify content considered toxic, offensive, or indecent as safe.
223
+ Licensing: | Governing Terms: Use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama2/LICENSE).
224
+
225
+
226
+ ### Privacy
227
+
228
+ Field | Response
229
+ :------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------
230
+ Generatable or reverse engineerable personal information? | None Known
231
+ Protected class data used to create this model? | None Known
232
+ Was consent obtained for any personal data used? | None Known
233
+ How often is dataset reviewed? | Before Release
234
+ Is there provenance for all datasets used in training? | Yes
235
+ Does data labeling (annotation, metadata) comply with privacy laws? | Yes
236
+
237
+ ### Safety
238
+
239
+ Field | Response
240
+ :---------------------------------------------------|:----------------------------------
241
+ Model Application(s): | Prompt moderation for world generation
242
+ Describe the life critical impact (if present). | None Known
243
+ Use Case Restrictions: | Governing Terms: Use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama2/LICENSE).
244
+ Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face, and may become available on cloud providers' model catalog.
Cosmos-Guardrail1/blocklist/custom/blocklist ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ nude
2
+ naked
3
+ nudity
4
+ clothingless
5
+ undress
6
+ striptease
7
+ blood
8
+ horror
9
+ gross
10
+ gore
11
+ butcherly
12
+ brutal
13
+ zombie
14
+ crucifixion
15
+ secretion
16
+ horrific
17
+ disgusting
18
+ carnage
19
+ creepy
20
+ grotesque
21
+ gruesome
22
+ macabre
23
+ freaky
24
+ morbid
25
+ hideous
26
+ bloodstream
27
+ horrifying
28
+ hemorrhage
29
+ lurid
30
+ sordid
31
+ bloodthirsty
32
+ ghastly
33
+ gratuitous
34
+ nightmarish
35
+ savagery
36
+ cronenberg
37
+ sadism
38
+ salacious
39
+ barbarity
40
+ gunplay
41
+ heart wrenching
42
+ ghoulish
43
+ tawdry
44
+ nauseating
45
+ titillating
46
+ bloodthirsty
47
+ pulpy
48
+ systole
49
+ fetishistic
50
+ sanguinary
51
+ discomforting
52
+ bulletstorm
53
+ slaughterous
54
+ sanguineous
55
+ bespatter
56
+ beflake
57
+ deskin
58
+ deskinned
59
+ deskinning
60
+ lifeless
61
+ bleeding
62
+ The Nightmare Before Christmas
63
+ Snow White and the Seven Dwarfs
64
+ Snow White
65
+ the Seven Dwarfs
66
+ Baymax
67
+ Big Hero 6
68
+ zootopia
69
+ aristocats
70
+ Mary Poppins
71
+ Inside Out
72
+ Nemo
73
+ Finding Nemo
74
+ Monsters, Inc.
75
+ Buzz Lightyear
76
+ DuckTales
77
+ 101 Dalmatians
78
+ Lilo & Stitch
79
+ Mickey Mouse
80
+ Minnie Mouse
81
+ Mary Poppins
82
+ Mulan
83
+ The Lion King
84
+ Oliver & Company
85
+ Dumbo
86
+ Bugs Bunny
87
+ Daffy Duck
88
+ Porky Pig
89
+ Elmer Fudd
90
+ Tweety Bird
91
+ Sylvester the Cat
92
+ Yosemite Sam
93
+ Foghorn Leghorn
94
+ Marvin the Martian
95
+ Pep\u00e9 le Pew
96
+ Superman
97
+ Batman
98
+ Wonder Woman
99
+ Green Lantern
100
+ The Flash
101
+ Aquaman
102
+ Harry Potter
103
+ Frodo Baggins
104
+ Gandalf the Grey
105
+ Bilbo Baggins
106
+ The Joker
107
+ Lex Luthor
108
+ Darkseid
109
+ Sinestro
110
+ Brainiac
111
+ Black Adam
112
+ Ra's al Ghul
113
+ Mr. Freeze
114
+ Lord Voldemort
115
+ Tom and Jerry
116
+ Scooby-Doo
117
+ Sylvester & Tweety
118
+ The Flintstones
119
+ Johnny Bravo
120
+ Popeye
121
+ Yogi Bear
122
+ Ant-Man
123
+ Captain America
124
+ Captain Marvel
125
+ Hawkeye
126
+ Magneto
127
+ She-Hulk
128
+ Silver Surfer
129
+ Spider-Man
130
+ Spider-Woman
131
+ Star-Lord
132
+ Thanos
133
+ Super Mario
134
+ Princess Peach
135
+ Bowser
136
+ Toadette
137
+ Yoshi
138
+ Wario
139
+ Waluigi
140
+ Donkey Kong
141
+ Diddy Kong
142
+ Rosalina
143
+ Bowser Jr.
144
+ Koopaling
145
+ Princess Zelda
146
+ Ganondorf
147
+ Pikachu
148
+ Charizard
149
+ Bulbasaur
150
+ Squirtle
151
+ Jigglypuff
152
+ Meowth
153
+ Lucario
154
+ Greninja
155
+ Mewtwo
156
+ Eevee
157
+ Trump
158
+ Monet
159
+ Mona Lisa
160
+ Jensen Huang
161
+ Mark Zuckerberg
162
+ Avatar
163
+ Obama
164
+ Oprah Winfrey
165
+ Tom Cruise
166
+ Lady Gaga
167
+ Kim Kardashian
168
+ Taylor Swift
169
+ Jennifer Lopez
170
+ 3M
171
+ Acura
172
+ Adidas
173
+ Airpods
174
+ Armani
175
+ AstraZeneca
176
+ Aston Martin
177
+ AMD
178
+ Amy Somerville
179
+ Anthony Theakston
180
+ AT&T
181
+ Audi
182
+ Aventador
183
+ Barbie
184
+ Batman
185
+ Batmobile
186
+ Bayer
187
+ Bently
188
+ BMW
189
+ Boston Dynamics
190
+ Blue Origin
191
+ Bosch
192
+ Brawl Stars
193
+ Brokis
194
+ Budweiser
195
+ Burger King
196
+ Bugatti
197
+ Burberry
198
+ Buick
199
+ Cadiliac
200
+ Canon
201
+ Cartier
202
+ Cassina
203
+ Chanel
204
+ Chick-fil-A
205
+ Cisco
206
+ Chevron
207
+ Chromebook
208
+ Chrystler
209
+ Citroen
210
+ Colgate
211
+ CocaCola
212
+ Countach
213
+ DC Comics
214
+ Daimler
215
+ Dell
216
+ DHL
217
+ Dior
218
+ Disney
219
+ Duracell
220
+ Dunkin Donuts
221
+ Eichholtz
222
+ Entler Studio
223
+ Elemento
224
+ Electrolux
225
+ Estee Lauder
226
+ Exxon
227
+ Fedex
228
+ Ferrari
229
+ Ferdinand Kramer
230
+ Fiskars
231
+ Fisker
232
+ Ford
233
+ Fortnite
234
+ Gatorade
235
+ Gandalf
236
+ Gameboy
237
+ Gamecube
238
+ General Motors
239
+ Gillette
240
+ Glock
241
+ GMC
242
+ Graef
243
+ Grant Featherston Contour
244
+ Gucci
245
+ Gulfstream
246
+ Gundam
247
+ Haier
248
+ Harley Davidson
249
+ Harry Potter
250
+ Heineken
251
+ Hennessy
252
+ Hermes
253
+ Hitachi
254
+ Hogwarts
255
+ Homepod
256
+ Honda
257
+ Honeywell
258
+ Hoka
259
+ Huawei
260
+ Huracan
261
+ Ikea
262
+ Imac
263
+ Ipad
264
+ Iphone
265
+ Ipod
266
+ Isuzu
267
+ Infiniti
268
+ Intel
269
+ Jabulani
270
+ John Deere
271
+ John Pomp Studios
272
+ Kelloggs
273
+ KFC
274
+ Kia
275
+ Land Rover
276
+ Lamborghini
277
+ Lancel
278
+ Lego
279
+ Lenovo
280
+ Lexus
281
+ LG
282
+ L'Oreal
283
+ Lockheed
284
+ Louis Vuitton
285
+ Lululemon
286
+ Macbook
287
+ Martinelli Luce
288
+ Mattel
289
+ Mazda
290
+ McDonalds
291
+ McDonald's
292
+ McClaren
293
+ Medtronic
294
+ Mercedes
295
+ Mettler Toledo
296
+ Michelin
297
+ Microsoft
298
+ Mini Cooper
299
+ Mitsubishi
300
+ Miura
301
+ MLB
302
+ Mondial
303
+ Montblanc
304
+ Motopanfilo
305
+ Motorola
306
+ Mortal Kombat
307
+ Murci\u00e9lago
308
+ N64
309
+ NBA
310
+ NCAA
311
+ Nike
312
+ Nintendo
313
+ Nissan
314
+ Northrop Grumman
315
+ Nokia
316
+ NVIDIA
317
+ Oakley
318
+ Panasonic
319
+ Pantene
320
+ Piaget
321
+ Pepsi
322
+ Peugeot
323
+ Philips
324
+ Playstation
325
+ Poltrona Frau
326
+ Porsche
327
+ Prada
328
+ Publix
329
+ Purina
330
+ Rakuten
331
+ Rayban
332
+ Raytheon
333
+ Reebok
334
+ Red Bull
335
+ Renault
336
+ Rimet
337
+ Rivian
338
+ Roche
339
+ Rolex
340
+ Rolls Royce
341
+ Saleen
342
+ Samsung
343
+ Schwan-Stabilo
344
+ Serapian
345
+ Shelby
346
+ Siemens
347
+ SpaceX
348
+ Starbucks
349
+ Stanley Cup
350
+ Stavros
351
+ Steiner Optics
352
+ Sonos
353
+ Sony
354
+ Skidata
355
+ Superman
356
+ Subaru
357
+ Suzuki
358
+ Taylormade
359
+ Tesla
360
+ Terminator
361
+ Toyota
362
+ Tuttuno
363
+ USPS
364
+ Vespa
365
+ Verizon
366
+ Volocopter
367
+ Volvo
368
+ Volkswagen
369
+ Walmart
370
+ Wii
371
+ WonderGlass
372
+ Woolworths
373
+ Xiaomi
374
+ Xbox
375
+ YKK
376
+ Zaha Hadid
377
+ Zuny
378
+ war
379
+ torture
380
+ murder
381
+ sniper
382
+ shotgun
383
+ rifle
Cosmos-Guardrail1/blocklist/exact_match/blocked ADDED
@@ -0,0 +1,1414 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Abu
2
+ Adams
3
+ Adele
4
+ Adonis Creed
5
+ Aerith Gainsborough
6
+ Agatha Harkness
7
+ Agnes
8
+ Ahri
9
+ Ahsoka Tano
10
+ Aku
11
+ Akuma
12
+ Aladdin
13
+ Alan Partridge
14
+ Alex
15
+ Alex Levy
16
+ Alex the Lion
17
+ Ali G
18
+ Alice
19
+ Alpha Pig
20
+ Alphonse Elric
21
+ Alyx Vance
22
+ America Chavez
23
+ Amethyst
24
+ Amicia de Rune
25
+ Anakin
26
+ Anakin Skywalker
27
+ Anastasia
28
+ Anastasia Tremaine
29
+ Angelica Pickles
30
+ Angelina Ballerina
31
+ Angie
32
+ Angus
33
+ Anna
34
+ Annie
35
+ Anpanman
36
+ Ant-Man
37
+ Anthony Edwards
38
+ Anton Chigurh
39
+ Anton Ego
40
+ Apollo Justice
41
+ Aqua Teen Carl
42
+ Aquaman
43
+ Archie Andrews
44
+ Archimedes
45
+ Ariana Grande
46
+ Ariel
47
+ Arkwright
48
+ Arlo
49
+ Arnim Zola
50
+ Arnold Shortman
51
+ Arrietty
52
+ Arthas Menethil
53
+ Arthur
54
+ Arthur Morgan
55
+ Arthur Nudge
56
+ Arthur Read
57
+ Ash Ketchum
58
+ Ashitaka
59
+ Asterix
60
+ Astrid
61
+ Astro Boy
62
+ Astroboy
63
+ Atom Ant
64
+ Atreus
65
+ Aunt Jemima
66
+ Aviva Corcovado
67
+ B.O.B.
68
+ Baba Looey
69
+ Baba Voss
70
+ Baby Bop
71
+ Baby Yoda
72
+ Bad Bunny
73
+ Bagheera
74
+ Baldrick
75
+ Baloo
76
+ Balthazar Bratt
77
+ Bambi
78
+ Bamm-Bamm Rubble
79
+ Barbie
80
+ Barley Lightfoot
81
+ Barney
82
+ Barney Rubble
83
+ Barnyard Dawg
84
+ Baron Humbert von Gikkingen
85
+ Barry B. Benson
86
+ Bart
87
+ Bart Simpson
88
+ Bartok
89
+ Bastion Narrator
90
+ Batgirl
91
+ Batman
92
+ Baymax
93
+ Bayonetta
94
+ Baze Malbus
95
+ BB-8
96
+ Beaky Buzzard
97
+ Beast and Belle
98
+ Beast Boy
99
+ Beavis
100
+ Beetle Bailey
101
+ Belle and Beast
102
+ Belle and the Beast
103
+ Bender
104
+ Benjamin Buford \"Bubba\" Blue
105
+ Benson
106
+ Berlioz
107
+ Bertie
108
+ Betty Boop
109
+ Betty Cooper
110
+ Betty Rubble
111
+ Bicycle Repair Man
112
+ Biden
113
+ Biff Tannen
114
+ Big Boss
115
+ Big Daddy
116
+ Big Nate
117
+ Biggie
118
+ Biggus Dickus
119
+ Bikini Bottom
120
+ Bill Gates
121
+ Bill the Cat
122
+ Billie Eilish
123
+ Billy Mack
124
+ Birdie
125
+ Bishop
126
+ Bitzer
127
+ BJ
128
+ Black Adam
129
+ Black Knight
130
+ Black Panther
131
+ Black Widow
132
+ Blackadder
133
+ Blathers
134
+ Blondie Bumstead
135
+ Blue Beetle (Jaime Reyes)
136
+ BMO
137
+ Bo Peep
138
+ Bo-Katan Kryze
139
+ Bob Parr
140
+ Bob the Builder
141
+ Bob the Minion
142
+ Boba Fett
143
+ Bobby Hill
144
+ Boo
145
+ Boo-Boo Bear
146
+ Boog
147
+ Booker DeWitt
148
+ Boomhauer
149
+ Bow Lion
150
+ Bowser
151
+ Bowser Jr.
152
+ Bradley Jackson
153
+ Brain (Alan Powers)
154
+ Brainiac
155
+ Brainy Smurf
156
+ Brak
157
+ Brian Cohen
158
+ Bridget
159
+ Brock
160
+ Brock Samson
161
+ Brother Maynard
162
+ Bruno Mars
163
+ Buchanan
164
+ Bud Brigman
165
+ Buddy the Elf
166
+ Buddy Tyrannosaurus
167
+ Bugs Bunny
168
+ Bullwinkle
169
+ Buster Baxter
170
+ Buster Moon
171
+ Butt Head
172
+ Butt-Head
173
+ ButtHead
174
+ Buzz Lightyear
175
+ BuzzBee
176
+ C-3PO
177
+ Caesar
178
+ Caillou
179
+ Calcifer
180
+ Calvin
181
+ Calvin's Mom
182
+ Cap'n Crunch
183
+ Cap'n Turbot
184
+ Cappy
185
+ Captain America
186
+ Captain Crunch
187
+ Captain Falcon
188
+ Captain Gutt
189
+ Captain Haddock
190
+ Captain Huggyface
191
+ Captain Mainwaring
192
+ Captain Rex
193
+ Carl Fredricksen
194
+ Carol Danvers (Captain Marvel)
195
+ Carrie White
196
+ Carter
197
+ Cartoon mouse
198
+ Casper
199
+ Casper the Friendly Ghost
200
+ Cassandra
201
+ Cassian Andor
202
+ Catbus
203
+ Catwoman
204
+ Celeste
205
+ Chara
206
+ Charlie B. Barkin
207
+ Charlie Brown
208
+ Charlie Dog
209
+ Charlie the Tuna
210
+ Charlotte
211
+ Chef Boyardee
212
+ Chell
213
+ Chester Cheetah
214
+ Chester V
215
+ Chewbacca
216
+ Chickaletta
217
+ Chicken Joe
218
+ Chihiro Ogino
219
+ Chirrut Imwe
220
+ Chloe
221
+ Chris Evans
222
+ Chris Kratt
223
+ Christopher Robin
224
+ Chuck Noland
225
+ Chuckie Finster
226
+ Chun-Li
227
+ Cinderella
228
+ Cindy Lou Who
229
+ Ciri
230
+ Claptrap
231
+ Clarabel
232
+ Clarence
233
+ Clarence Odbody
234
+ Clark Griswold
235
+ classical animation
236
+ Claude Cat
237
+ Cleo
238
+ Cleveland
239
+ Clifford
240
+ Clint
241
+ Clinton
242
+ Clippy
243
+ Cloud Strife
244
+ Clumsy Smurf
245
+ Coach Beard
246
+ Coco
247
+ Cody Maverick
248
+ Cogsworth
249
+ Colonel Hathi
250
+ Colonel Miles Quaritch
251
+ Colonel Sanders
252
+ Commander Shepard
253
+ Compo Simmonite
254
+ Connie Maheswaran
255
+ Constantine
256
+ Coolidge
257
+ Coraline Jones
258
+ Cortana
259
+ Cory Ellison
260
+ Count Chocula
261
+ Count Dooku
262
+ Count Dracula
263
+ Cousin Eddie
264
+ Cranky
265
+ Crash Bandicoot
266
+ Crisbell
267
+ Cristiano Ronaldo
268
+ Cruella de Vil
269
+ Cruella de Ville
270
+ Cuphead
271
+ Curious George
272
+ Cyborg
273
+ Cyclops
274
+ D.Va
275
+ D.W. Read
276
+ Daddy Pig
277
+ Daddy Warbucks
278
+ Daffy Duck
279
+ Dagwood Bumstead
280
+ Daisy Duck
281
+ Dale Gribble
282
+ Daniel Tiger
283
+ Dante
284
+ Daphne Blake
285
+ Daredevil
286
+ Darkseid
287
+ Darth Vader
288
+ Dash Parr
289
+ David Brent
290
+ Deadpool
291
+ Deathstroke
292
+ Dee Dee
293
+ Del Boy
294
+ Demoman
295
+ Dennis
296
+ Dennis Mitchell
297
+ Devi D.
298
+ Dewey Duck
299
+ Dexter
300
+ Dib
301
+ Dib Membrane
302
+ Dick Tracy
303
+ Diddy Kong
304
+ Dig'em Frog
305
+ Dil Pickles
306
+ Dilbert
307
+ Din Djarin
308
+ Din Song
309
+ Disgust
310
+ Dixie Kong
311
+ Doc Hudson
312
+ Doctor Doom
313
+ Doctor Strange
314
+ Dogbert
315
+ Doja Cat
316
+ Don Lino
317
+ Don Pteranodon
318
+ Donald Duck
319
+ Donald Trump
320
+ Donkey Kong
321
+ Doom Slayer
322
+ Dora
323
+ Dora Marquez
324
+ Doraemon
325
+ Dorothy
326
+ Dorothy Gale
327
+ Dorothy the Dinosaur
328
+ Dorothy Turner
329
+ Dory
330
+ Doug Funnie
331
+ Dr. Cockroach
332
+ Dr. Frank-N-Furter
333
+ Dr. Girlfriend
334
+ Dr. Grace Augustine
335
+ Dr. Robotnik
336
+ Dr. Two Brains
337
+ Dracula
338
+ Drake
339
+ Drax
340
+ Drax the Destroyer
341
+ Drizella Tremaine
342
+ Dua Lipa
343
+ Duchess
344
+ Dudley Do-Right
345
+ Duffy Bear
346
+ Duke
347
+ Dumbo
348
+ Dwayne Johnson
349
+ Ebenezer Scrooge
350
+ Ed Bighead
351
+ Ed Sheeran
352
+ Eddie Valiant
353
+ Edgar Balthazar
354
+ Edith
355
+ Edna Mode
356
+ Edward
357
+ Edward Elric
358
+ Eep Crood
359
+ Eeyore
360
+ Egghead Jr.
361
+ Eisenhower
362
+ Elastigirl
363
+ Elektra
364
+ Ella
365
+ Ellen Ripley
366
+ Ellie
367
+ Elliot
368
+ Elmer Fudd
369
+ Elon Musk
370
+ Elroy Jetson
371
+ Elsa
372
+ Emile
373
+ Emily
374
+ Emily Dickinson
375
+ Emily Elizabeth Howard
376
+ Emma Watson
377
+ Emmett \"Doc\" Brown
378
+ Emperor Palpatine
379
+ Eren Yeager
380
+ Eric Cartman
381
+ Esmeralda
382
+ EVE
383
+ Evil Queen
384
+ Ewoks
385
+ Explosm Cyanide Character
386
+ Ezra Bridger
387
+ Fairy Godmother
388
+ Falco Lombardi
389
+ Father Ted Crilly
390
+ Felix the Cat
391
+ Ferb Fletcher
392
+ Ferdinand
393
+ Figaro
394
+ Fillmore
395
+ Finn
396
+ Finn the Human
397
+ Fiona
398
+ Fireman Sam
399
+ Fishlegs
400
+ Flint Lockwood
401
+ Flit
402
+ Flo
403
+ Flounder
404
+ Flynn Rider
405
+ Foghorn Leghorn
406
+ Ford
407
+ Forky
408
+ Forrest Gump
409
+ Fox McCloud
410
+ Francine Frensky
411
+ Francine Peters
412
+ Francois Turbot
413
+ Frank Spencer
414
+ Franklin
415
+ Fred
416
+ Fred Flintstone
417
+ Frieza
418
+ Frigga
419
+ Frisk
420
+ Frosty the Snowman
421
+ Frou-Frou
422
+ Frozone
423
+ Frylock
424
+ Fudgie the Whale
425
+ Gabi
426
+ Gabriela
427
+ Gambit
428
+ Gamora
429
+ Gandalf
430
+ Ganondorf
431
+ Garfield
432
+ Garfield's Nermal
433
+ Gargamel
434
+ Garnet
435
+ Garrus Vakarian
436
+ Gaz
437
+ Geico Gecko
438
+ General Grievous
439
+ Genie
440
+ Genji
441
+ Geoffrey the Giraffe
442
+ George Bailey
443
+ George Bush
444
+ George H. W. Bush
445
+ George Jetson
446
+ George McFly
447
+ George Pig
448
+ George W. Bush
449
+ Gerald
450
+ Gerald Johanssen
451
+ Geraldine Granger
452
+ Geralt
453
+ Geralt of Rivia
454
+ Ghost Rider
455
+ Gideon
456
+ Gidget
457
+ Ginny Grainger
458
+ GIR
459
+ GLaDOS
460
+ Globox
461
+ Gloria
462
+ Gloria the Hippo
463
+ Gobber
464
+ Gohan
465
+ Goko
466
+ Goku
467
+ Goldfish Cracker
468
+ Gon Freecss
469
+ Goofy
470
+ Gordon
471
+ Gordon Freeman
472
+ Gossamer
473
+ Gotham City
474
+ Gran
475
+ Gran'ma Ben
476
+ Grand Admiral Thrawn
477
+ Grandmaster
478
+ Granny
479
+ Green Lantern (Hal Jordan)
480
+ Greg Universe
481
+ Gregg
482
+ Grimace
483
+ Grogu
484
+ Grogu (Baby Yoda)
485
+ Gromit
486
+ Groot
487
+ Gru
488
+ Grug Crood
489
+ Guile
490
+ Gwen Stacy
491
+ Hagar the Horrible
492
+ Haku
493
+ HAL 9000
494
+ Hal Stewart / Tighten
495
+ Hamm
496
+ Hammy
497
+ Han Solo
498
+ Hancock
499
+ Handsome Jack
500
+ Haniwa
501
+ Happy Noodle Boy
502
+ Harding
503
+ Harley Quinn
504
+ Harold
505
+ Harris
506
+ Harrison
507
+ Harry Potter
508
+ Harry Styles
509
+ Harry Tasker
510
+ Hat Kid
511
+ Hawkeye
512
+ Hayes
513
+ Heat Miser
514
+ Heather
515
+ Hector
516
+ Hector the Bulldog
517
+ Heffer Wolfe
518
+ Hei Hei
519
+ Heihachi Mishima
520
+ Heimdall
521
+ Hela
522
+ Helen Hunt
523
+ Helen Tasker
524
+ Helga Pataki
525
+ Hello Kitty
526
+ Henery Hawk
527
+ Henry
528
+ Henry the Octopus
529
+ Hera Syndulla
530
+ Hercules
531
+ Hermey the Elf
532
+ Hi-5
533
+ Hiccup
534
+ Hiro
535
+ Hisoka
536
+ Hobbes
537
+ Hogwarts
538
+ Homer
539
+ Homer Simpson
540
+ Homestar Runner
541
+ Homsar
542
+ Honest John
543
+ Hoover
544
+ Horton
545
+ Howard Hughes
546
+ Hubie
547
+ Huckleberry Hound
548
+ Huey Duck
549
+ Hugo de Rune
550
+ Hulk
551
+ Human Torch
552
+ Humphrey Bogart
553
+ Hyacinth Bucket
554
+ H\u00e9ctor Rivera
555
+ Ian Lightfoot
556
+ Ice King
557
+ Incontinentia Buttocks
558
+ Indiana Jones
559
+ Inkling
560
+ Inspector Clouseau
561
+ Inspector Gadget
562
+ Inuyasha
563
+ Invader Skoodge
564
+ Invisible Woman
565
+ Iron Fist
566
+ Iron Man
567
+ Isaac Clarke
568
+ Isabelle
569
+ Itchy Itchiford
570
+ Ivy Valentine
571
+ Ja Morant
572
+ Jack Dawson
573
+ Jack Skellington
574
+ Jack-Jack
575
+ Jack-Jack Parr
576
+ Jackie Brown
577
+ Jackson
578
+ Jafar
579
+ Jailbreak
580
+ Jake from State Farm
581
+ Jake Sully
582
+ Jake the Dog
583
+ James
584
+ James Bond
585
+ James Henry Trotter
586
+ Jane Jetson
587
+ Jane Porter
588
+ Jasmine
589
+ Jean Grey
590
+ Jedi
591
+ Jeff
592
+ Jefferson
593
+ Jennifer Lopez
594
+ Jennifer Parker
595
+ Jenny Curran
596
+ Jerry
597
+ Jesper
598
+ Jess (the Cat)
599
+ Jessica Jones
600
+ Jessica Rabbit
601
+ Jessie
602
+ Jett
603
+ Jiji
604
+ Jill Valentine
605
+ Jim Raynor
606
+ Jiminy Cricket
607
+ Jimmy Z
608
+ Jin Kazama
609
+ Jinx
610
+ Joe Camel
611
+ Joe Gardner
612
+ Joe Rogan
613
+ Joel
614
+ Joel Miller
615
+ Johann Gambolputty...
616
+ John Connor
617
+ John Marston
618
+ John McClane
619
+ John Smith
620
+ Johnny
621
+ Johnny Bravo
622
+ Johnny C. (Nny)
623
+ Johnny Loughran
624
+ Johnson
625
+ JoJo McDodd
626
+ Jon Arbuckle
627
+ Josie McCoy
628
+ Judge Doom
629
+ Judy Hopps
630
+ Judy Jetson
631
+ Julian Pearce
632
+ Jumanji
633
+ Justin Bieber
634
+ Jyn Erso
635
+ K-2SO
636
+ K.K. Slider
637
+ Kaa
638
+ Kai
639
+ Kakashi Hatake
640
+ Kamala Harris
641
+ Kamala Khan (Ms. Marvel)
642
+ Kanga
643
+ Kanye West
644
+ Katchoo
645
+ Kate Bishop
646
+ Katie Mitchell
647
+ Kazooie
648
+ Kazuya Mishima
649
+ Keeley Jones
650
+ Ken
651
+ Ken Masters
652
+ Kendrick Lamar
653
+ Kennedy
654
+ Kerrigan
655
+ Kevin
656
+ Kevin McCallister
657
+ Kevin the Minion
658
+ Kiki
659
+ Killjoy
660
+ Killmonger (Erik Stevens)
661
+ Killua Zoldyck
662
+ Kim Kardashian
663
+ King Arthur
664
+ King Candy
665
+ King Dedede
666
+ King Gristle Jr.
667
+ King Julien
668
+ King Knight
669
+ King Louie
670
+ King of the Hill
671
+ King Triton
672
+ King Vitamin
673
+ Kingpin
674
+ Kirby
675
+ Kitana
676
+ Kofun
677
+ Koki
678
+ Kool-Aid
679
+ Kool-Aid Man
680
+ Korath
681
+ Korg
682
+ Kowalski
683
+ Kraglin
684
+ Kratos
685
+ Kris Kringle
686
+ Kristoff
687
+ Kurapika
688
+ Kuzco
689
+ Kyle Reese
690
+ Kylie Jenner
691
+ Kylo Ren
692
+ Lady Eboshi
693
+ Lady Gaga
694
+ Lady Sif
695
+ Lady Tremaine
696
+ LaMelo Ball
697
+ Lando Calrissian
698
+ Lara
699
+ Lara Croft
700
+ Larry the Lobster
701
+ Lars Barriga
702
+ Leanne Grayson
703
+ LeBron James
704
+ Lenny
705
+ Lenore
706
+ Leon Kennedy
707
+ Levi Ackerman
708
+ Lewis Hamilton
709
+ Lex Luthor
710
+ Liara T'Soni
711
+ Lieutenant Dan Taylor
712
+ Light Yagami
713
+ Lightning McQueen
714
+ Lil DeVille
715
+ Lilo
716
+ Lincoln
717
+ Linda Gunderson
718
+ Lindsey Brigman
719
+ Linus
720
+ Linus van Pelt
721
+ Lisa
722
+ Lisa Simpson
723
+ Little Caesar
724
+ Little Orphan Annie
725
+ Liu Kang
726
+ Logan
727
+ Loki
728
+ Lola Bunny
729
+ Lord Shen
730
+ Lorraine Baines
731
+ Lotso
732
+ Louie Duck
733
+ Luanne Platter
734
+ Lucas
735
+ Lucifer
736
+ Lucky Eddie
737
+ Lucky the Leprechaun
738
+ Lucy Van Pelt
739
+ Luigi
740
+ Luke
741
+ Luke Cage
742
+ Luke Skywalker
743
+ Luke Triton
744
+ Lumberjack
745
+ Lumi\u00e8re
746
+ M'Baku
747
+ Mace Windu
748
+ Madam Mim
749
+ Madame Adelaide Bonfamille
750
+ Madeline
751
+ Madison
752
+ Mae Borowski
753
+ Mafalda
754
+ Maggie Simpson
755
+ Maghra
756
+ Magilla Gorilla
757
+ Magneto
758
+ Mai Shiranui
759
+ Maisy
760
+ Malcolm Tucker
761
+ Maleficent
762
+ Mandalorian
763
+ Mandark
764
+ Mando
765
+ Manny
766
+ Marceline
767
+ Margaret Tiger
768
+ Marge
769
+ Marge Simpson
770
+ Margo
771
+ Margo Leadbetter
772
+ Maria Hill
773
+ Maria Rambeau
774
+ Mario
775
+ Mark Zuckerberg
776
+ Marlin
777
+ Marmaduke
778
+ Marshall
779
+ Martian Manhunter
780
+ Martin Bryce
781
+ Martin Kratt
782
+ Marty
783
+ Marty McFly
784
+ Marty the Zebra
785
+ Marvin Acme
786
+ Marvin the Martian
787
+ Mary Poppins
788
+ Master Chief
789
+ Master Shake
790
+ Mater
791
+ Mavis Dracula
792
+ Max Verstappen
793
+ Maximus
794
+ Maya Fey
795
+ Mayor Goodway
796
+ McKinley
797
+ Meatwad
798
+ Meeko
799
+ Meena
800
+ Mega Man
801
+ Megamind
802
+ Megara
803
+ Mei Kusakabe
804
+ Mel
805
+ Melman
806
+ Melman the Giraffe
807
+ Meowth
808
+ Merida
809
+ Merlin
810
+ Merryweather
811
+ Meta Knight
812
+ Metro Man
813
+ Micah Keith
814
+ Michigan J. Frog
815
+ Mickey
816
+ Miek
817
+ Mighty Mouse
818
+ Miguel
819
+ Miguel Rivera
820
+ Mike Wazowski
821
+ Miles Edgeworth
822
+ Miles Morales
823
+ Miley Cyrus
824
+ Millennium Falcon
825
+ Milo
826
+ Minion
827
+ Minnie Mouse
828
+ Miranda
829
+ Misa Amane
830
+ Misato Katsuragi
831
+ Mitch Kessler
832
+ Mitsurugi
833
+ Moana
834
+ Mojo Jojo
835
+ Monica Rambeau
836
+ Monkey D. Luffy
837
+ Monkeybone
838
+ Monroe
839
+ Monstro
840
+ Mordecai
841
+ Morris the Cat
842
+ Morty Smith
843
+ Mowgli
844
+ Mr. Bean
845
+ Mr. Clean
846
+ Mr. Creosote
847
+ Mr. Eric Praline
848
+ Mr. Incredible
849
+ Mr. Krabs
850
+ Mr. Peabody
851
+ Mr. Peanut
852
+ Mr. Potato Head
853
+ Mr. Potatohead
854
+ Mr. Toad
855
+ Mr. Wilson
856
+ Mrs. Brisby
857
+ Mrs. Brown
858
+ Mrs. Gump
859
+ Mrs. Merton
860
+ Mrs. Potts
861
+ Mrs. Spider
862
+ Ms. Pac-Man
863
+ Mufasa
864
+ Muffy Crosswire
865
+ Mugman
866
+ Mugsy
867
+ Mulan
868
+ Mummy Pig
869
+ Mushu
870
+ Nakia
871
+ Nala
872
+ Nami
873
+ Namor
874
+ Nancy
875
+ Naru
876
+ Naruto Uzumaki
877
+ Nate Shelley
878
+ Nathan
879
+ Nathan Drake
880
+ Nausica\u00e4
881
+ Nefertari Vivi
882
+ Negasonic Teenage Warhead
883
+ Nemo
884
+ Neo
885
+ Ness
886
+ Nessa Jenkins
887
+ Newt (Rebecca Jorden)
888
+ Neytiri
889
+ Nick Fury
890
+ Nick Wilde
891
+ Nicki Minaj
892
+ Nigel
893
+ Nightwing
894
+ Nina Williams
895
+ Nixon
896
+ No-Face
897
+ Nobita Nobi
898
+ Noddy
899
+ Norman
900
+ Norman Babcock
901
+ Norman Price
902
+ Obama
903
+ Obelix
904
+ Obi-Wan Kenobi
905
+ Octoling
906
+ Odie
907
+ Odin
908
+ Okoye
909
+ Olaf
910
+ Olive Oyl
911
+ Olivia Rodrigo
912
+ Opus
913
+ Ori
914
+ Oscar
915
+ Oswald
916
+ Ozzie
917
+ Pac-Man
918
+ Paddington Bear
919
+ Padm\u00e9 Amidala
920
+ Palpatine
921
+ Papa Smurf
922
+ Pappa Smurf
923
+ Papyrus
924
+ Pascal
925
+ Patrick Mahomes
926
+ Patrick Star
927
+ Patsy
928
+ Patsy Stone
929
+ Patti Mayonnaise
930
+ Pazu
931
+ Pebbles Flintstone
932
+ Peggy Carter
933
+ Peggy Hill
934
+ Penelope Pussycat
935
+ Pepe Le Pew
936
+ Peppa Pig
937
+ Percy
938
+ Perdita
939
+ Peridot
940
+ Perry
941
+ Perry the Platypus
942
+ Peter B. Parker
943
+ Peter Griffin
944
+ Peter Pan
945
+ Peter Parker
946
+ Peter Rabbit
947
+ Phil DeVille
948
+ Phineas Flynn
949
+ Phoebe Heyerdahl
950
+ Phoenix Wright
951
+ Phoney Bone
952
+ Piglet
953
+ Pikachu
954
+ Pillsbury Doughboy
955
+ Pingu
956
+ Pink Panther
957
+ Pinocchio
958
+ Plague Knight
959
+ Play-Doh Pete
960
+ Pluto
961
+ Po
962
+ Pocahontas
963
+ Poe Dameron
964
+ Polk
965
+ PomPom
966
+ Pongo
967
+ Pontius Pilate
968
+ Ponyo
969
+ Popeye
970
+ Poppin' Fresh (Pillsbury Doughboy)
971
+ Poppy Parnell
972
+ Porkchop
973
+ Porky Pig
974
+ Post Malone
975
+ Postman Pat
976
+ Potato Head
977
+ President
978
+ Prince Charming
979
+ Prince Eric
980
+ Prince Phillip
981
+ Prince Wednesday
982
+ Princess Bubblegum
983
+ Princess Leia
984
+ Princess Leia Organa
985
+ Princess Mononoke
986
+ Princess Peach
987
+ Princess Presto
988
+ Professor Layton
989
+ Professor X
990
+ Proto Man
991
+ Pumbaa
992
+ Punisher
993
+ Puss
994
+ Puss in Boots
995
+ Puss n Boots
996
+ Pyramid Head
997
+ Pyro
998
+ Queen Kane
999
+ Queen Xenomorph
1000
+ Qui-Gon Jinn
1001
+ Quick Draw McGraw
1002
+ Quicksilver
1003
+ R2-D2
1004
+ Rabbids
1005
+ Rafael
1006
+ Raiden
1007
+ Ralph
1008
+ Ralph Wolf
1009
+ Ralphie Parker
1010
+ Randall Boggs
1011
+ Rapunzel
1012
+ Rayman
1013
+ Reagan
1014
+ Rebecca Welton
1015
+ Red and Rover
1016
+ Red Skull
1017
+ Rei Ayanami
1018
+ Reinhardt
1019
+ Remy
1020
+ Ren H\u00f6ek
1021
+ Resetti
1022
+ Rex
1023
+ Rey
1024
+ Reyna
1025
+ Rheneas
1026
+ Rhett Butler
1027
+ Richie Rich
1028
+ Rick
1029
+ Rick Mitchell
1030
+ Rick Sanchez
1031
+ Rico
1032
+ Ridley
1033
+ Rigby
1034
+ Rigsby
1035
+ Rihanna
1036
+ RJ
1037
+ Road Runner
1038
+ Robin (Dick Grayson)
1039
+ Robo-Dog
1040
+ Rocket Raccoon
1041
+ Rocko
1042
+ Rocky Balboa
1043
+ Rodney Copperbottom
1044
+ Rodney Trotter
1045
+ Roger Klotz
1046
+ Roger Rabbit
1047
+ Roger the Shrubber
1048
+ Ronald McDonald
1049
+ Ronan the Accuser
1050
+ Roo
1051
+ Roosevelt
1052
+ Roronoa Zoro
1053
+ Rosalina
1054
+ Rose DeWitt Bukater
1055
+ Rosie
1056
+ Rosita
1057
+ Roxanne Ritchi
1058
+ Roy Kent
1059
+ Roy Mustang
1060
+ Rudolph
1061
+ Ruffnut
1062
+ Russell
1063
+ Ryder
1064
+ Ryu
1065
+ Sabine Wren
1066
+ Sadie Miller
1067
+ Sage
1068
+ Sailor Moon
1069
+ Sakura Haruno
1070
+ Salad Fingers
1071
+ Sam
1072
+ Sam Fisher
1073
+ Sam Sheepdog
1074
+ Sam Sparks
1075
+ Samurai Jack
1076
+ Samus Aran
1077
+ Sandy Cheeks
1078
+ Sandy Crood
1079
+ Santa Claus
1080
+ Santa Claus (Kurt Russell)
1081
+ Sarah Connor
1082
+ Sarge
1083
+ Sasuke
1084
+ Satsuki
1085
+ Saw Gerrera
1086
+ Scarlet Overkill
1087
+ Scarlet Witch
1088
+ Scarlett Johansson
1089
+ Scarlett O'Hara
1090
+ Schroeder
1091
+ Scooby
1092
+ Scooby Doo
1093
+ Scooby-Doo
1094
+ Scooby-Dum
1095
+ Scott Calvin
1096
+ Scrat
1097
+ Scrooge
1098
+ Scrooge McDuck
1099
+ Scuttle
1100
+ Sean Turner
1101
+ Sebastian
1102
+ Secret Squirrel
1103
+ Seiji Amasawa
1104
+ Selena Gomez
1105
+ Senua
1106
+ Sephiroth
1107
+ Sesshomaru
1108
+ Shadow the Hedgehog
1109
+ Shaggy Rogers
1110
+ Shakira
1111
+ Shang
1112
+ Shang-Chi
1113
+ Sharon Carter
1114
+ Shaun
1115
+ Shawn Mendes
1116
+ Shazam
1117
+ Sheeta
1118
+ Shere Khan
1119
+ Sherman
1120
+ Shifu
1121
+ Shin-chan
1122
+ Shinji Ikari
1123
+ Shiny Pteranodon
1124
+ Shizuka Minamoto
1125
+ Shizuku Tsukishima
1126
+ Shovel Knight
1127
+ Shrek
1128
+ Shuri
1129
+ Sid
1130
+ Siegfried
1131
+ Silver Surfer
1132
+ Simba
1133
+ Sir Bedevere
1134
+ Sir Galahad the Pure
1135
+ Sir Lancelot the Brave
1136
+ Sir Robin
1137
+ Sir Topham Hatt
1138
+ Skarloey
1139
+ Skye
1140
+ Skywalker
1141
+ Sluggo
1142
+ Smiley Bone
1143
+ Smokey Bear
1144
+ Smurf
1145
+ Smurfette
1146
+ Snagglepuss
1147
+ Snap, Crackle, and Pop
1148
+ Sniffles
1149
+ Sniper
1150
+ Snoopy
1151
+ Snotlout
1152
+ Snow Miser
1153
+ Snow White
1154
+ Solaire of Astora
1155
+ Solid Snake
1156
+ Sonic the Hedgehog
1157
+ Sonic's Knuckles
1158
+ Sophie Hatter
1159
+ Spam Waitress
1160
+ Specter Knight
1161
+ Speedy Gonzales
1162
+ Spencer
1163
+ Spider-Man
1164
+ Spiderman
1165
+ Sponge Bob
1166
+ SpongeBob
1167
+ SpongeBob Square Pants
1168
+ SpongeBob SquarePants
1169
+ SpongeBob's Grandma
1170
+ Spuds MacKenzie
1171
+ Spyro
1172
+ Squall Leonhart
1173
+ Squidward Tentacles
1174
+ Srongbad
1175
+ Star Lord
1176
+ Star-Lord
1177
+ Starfire
1178
+ Stella
1179
+ Stephen Curry
1180
+ Steve
1181
+ Steven Universe
1182
+ Stewie Griffin
1183
+ Stimpy
1184
+ Stoick the Vast
1185
+ Stromboli
1186
+ Strong Bad
1187
+ Stuart Little
1188
+ Stuart the Minion
1189
+ Sulley
1190
+ Sully
1191
+ Sumo
1192
+ Suneo Honekawa
1193
+ Super Why
1194
+ Supergirl
1195
+ Superman
1196
+ Surtur
1197
+ Susan Murphy
1198
+ Susan Murphy / Ginormica
1199
+ Susan Walker
1200
+ Susie Carmichael
1201
+ Sven
1202
+ Swiper
1203
+ Sylvester
1204
+ T-1000
1205
+ T-800
1206
+ T-800 (The Terminator)
1207
+ T-Bone
1208
+ Taft
1209
+ Tai Lung
1210
+ Takeshi Goda (Gian)
1211
+ Talos
1212
+ Tamacti Jun
1213
+ Tank Girl
1214
+ Tarzan
1215
+ Tasmanian Devil
1216
+ Taylor
1217
+ Taylor Swift
1218
+ Taz
1219
+ Team Rocket
1220
+ Ted Lasso
1221
+ Ted Wiggins
1222
+ Teddy Ruxpin
1223
+ Teemo
1224
+ Terminator
1225
+ Terry Bogard
1226
+ Thanatos
1227
+ Thanos
1228
+ The \"It's\" Man
1229
+ The Aflac Duck
1230
+ The Android Robot
1231
+ The Apple Logo Face
1232
+ The Avengers
1233
+ The Beast and Belle
1234
+ The Brawny Lumberjack
1235
+ The Bride
1236
+ The Burger King
1237
+ The Butcher
1238
+ The California Raisins
1239
+ The Camel (Joe Camel)
1240
+ The Caterpillar
1241
+ The Charmin Bears
1242
+ The Cheerios Bee
1243
+ The Cheshire Cat
1244
+ The Collector
1245
+ The Conductor
1246
+ The Death Star
1247
+ The Energizer Bunny
1248
+ The Ewoks
1249
+ The Flash
1250
+ The French Taunter
1251
+ The Froot Brute
1252
+ The Geico Gecko
1253
+ The Ghost of Christmas Past
1254
+ The Ghost of Christmas Present
1255
+ The Ghost of Christmas Yet to Come
1256
+ The Goldfish Cracker
1257
+ The Green Giant
1258
+ The Grinch
1259
+ The Gumbys
1260
+ The Hamburglar
1261
+ The Joker
1262
+ The Jolly Green Giant
1263
+ The Killer Rabbit of Caerbannog
1264
+ The Knights Who Say \"Ni\"
1265
+ The Kool-Aid Man
1266
+ The Laughing Cow
1267
+ The Lego Minifigure
1268
+ The Liberty Mutual Emu
1269
+ The Little Green Sprout
1270
+ The Little Prince
1271
+ The M&M's Characters
1272
+ The Mad Hatter
1273
+ The Mandarin
1274
+ The Michelin Man
1275
+ The Missing Link
1276
+ The Monarch
1277
+ The Monopoly Man
1278
+ The Morton Salt Girl
1279
+ The Nesquik Bunny
1280
+ The Noid
1281
+ The Once-ler
1282
+ The Planters Peanut
1283
+ The Planters Peanut (Mr. Peanut)
1284
+ The Red and Yellow M&M's
1285
+ The Scrubbing Bubbles
1286
+ The Starbucks Mermaid
1287
+ The Sun (Raisin Bran)
1288
+ The Taco Bell Chihuahua
1289
+ The Travelocity Gnome
1290
+ The Trix Rabbit
1291
+ The Vault Hunters
1292
+ The Weeknd
1293
+ The White Rabbit
1294
+ Theo
1295
+ Thomas
1296
+ Thomas O'Malley
1297
+ Thor
1298
+ Thorn Harvestar
1299
+ Thrall
1300
+ Thunk Crood
1301
+ Tiana
1302
+ Tidus
1303
+ Tifa Lockhart
1304
+ Tigger
1305
+ Tigress
1306
+ Tim
1307
+ Tim Lockwood
1308
+ Tim the Enchanter
1309
+ Timmy
1310
+ Timmy Brisby
1311
+ Timon
1312
+ Tinker Bell
1313
+ Tintin
1314
+ Tiny Diamond
1315
+ Tiny Pteranodon
1316
+ Tiny Tim
1317
+ Toad
1318
+ Toby
1319
+ Tom
1320
+ Tom And Jerry
1321
+ Tom Holland
1322
+ Tom Nook
1323
+ Tommy Pickles
1324
+ Tony
1325
+ Tony the Tiger
1326
+ Top Cat
1327
+ Totoro
1328
+ Toucan Sam
1329
+ Tracker
1330
+ Travis Scott
1331
+ Trevor Phillips
1332
+ Triss Merigold
1333
+ Trix Rabbit
1334
+ Truman
1335
+ Trump
1336
+ Tuffnut
1337
+ Tweety Bird
1338
+ Tyler
1339
+ Ultron
1340
+ Uncle Ben
1341
+ Ursula
1342
+ Usagi Tsukino (Sailor Moon)
1343
+ Usagi Yojimbo
1344
+ Usopp
1345
+ Valerie Brown
1346
+ Valiente
1347
+ Valkyrie
1348
+ Van Buren
1349
+ Vanellope
1350
+ Vegeta
1351
+ Velma Dinkley
1352
+ Venom
1353
+ Verne
1354
+ Veronica Lodge
1355
+ Victor Frankenstein
1356
+ Victor Meldrew
1357
+ Violet Parr
1358
+ Vivo
1359
+ WALL-E
1360
+ Wallace
1361
+ Walter Hobbs
1362
+ Waluigi
1363
+ Wario
1364
+ Warren Cave
1365
+ Washington
1366
+ Wendy
1367
+ Wheatley
1368
+ Widowmaker
1369
+ Wilbur
1370
+ Wildcat
1371
+ Wile E. Coyote
1372
+ Will Hunting
1373
+ Will Smith
1374
+ Willie T. Stokes
1375
+ Wilma
1376
+ Wilma Flintstone
1377
+ Wilson
1378
+ Wimpy
1379
+ Winnie the Pooh
1380
+ Winry Rockbell
1381
+ Winter Soldier
1382
+ Witch Hazel
1383
+ Wolverine
1384
+ Wonder Red
1385
+ Wonder Woman
1386
+ Woody
1387
+ Woody Woodpecker
1388
+ Woofster
1389
+ WordGirl
1390
+ Wybie Lovat
1391
+ X-23
1392
+ X-Men
1393
+ Yasuo
1394
+ Yoda
1395
+ Yogi Bear
1396
+ Yon-Rogg
1397
+ Yondu
1398
+ Yosemite Sam
1399
+ Yoshi
1400
+ Yoshimitsu
1401
+ Yubaba
1402
+ Yukon Cornelius
1403
+ Yummy Mummy
1404
+ Yuna
1405
+ Zagreus
1406
+ Zatanna
1407
+ Zazu
1408
+ Zelda
1409
+ Zelda's Sheik
1410
+ Zendaya
1411
+ Zim
1412
+ Zorak
1413
+ Zuma
1414
+ Zurg
Cosmos-Guardrail1/blocklist/nltk_data/corpora/wordnet.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbda5ea6eef7f36a97a43d4a75f85e07fccbb4f23657d27b4ccbc93e2646ab59
3
+ size 10775600
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b16c23d738effbdc5789d7aa601397c13ba2819bf922fb904687f3f16657ed
3
+ size 4259017
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/README ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Pretrained Punkt Models -- Jan Strunk (New version trained after issues 313 and 514 had been corrected)
2
+
3
+ Most models were prepared using the test corpora from Kiss and Strunk (2006). Additional models have
4
+ been contributed by various people using NLTK for sentence boundary detection.
5
+
6
+ For information about how to use these models, please confer the tokenization HOWTO:
7
+ http://nltk.googlecode.com/svn/trunk/doc/howto/tokenize.html
8
+ and chapter 3.8 of the NLTK book:
9
+ http://nltk.googlecode.com/svn/trunk/doc/book/ch03.html#sec-segmentation
10
+
11
+ There are pretrained tokenizers for the following languages:
12
+
13
+ File Language Source Contents Size of training corpus(in tokens) Model contributed by
14
+ =======================================================================================================================================================================
15
+ czech.pickle Czech Multilingual Corpus 1 (ECI) Lidove Noviny ~345,000 Jan Strunk / Tibor Kiss
16
+ Literarni Noviny
17
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
18
+ danish.pickle Danish Avisdata CD-Rom Ver. 1.1. 1995 Berlingske Tidende ~550,000 Jan Strunk / Tibor Kiss
19
+ (Berlingske Avisdata, Copenhagen) Weekend Avisen
20
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
21
+ dutch.pickle Dutch Multilingual Corpus 1 (ECI) De Limburger ~340,000 Jan Strunk / Tibor Kiss
22
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
23
+ english.pickle English Penn Treebank (LDC) Wall Street Journal ~469,000 Jan Strunk / Tibor Kiss
24
+ (American)
25
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
26
+ estonian.pickle Estonian University of Tartu, Estonia Eesti Ekspress ~359,000 Jan Strunk / Tibor Kiss
27
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
28
+ finnish.pickle Finnish Finnish Parole Corpus, Finnish Books and major national ~364,000 Jan Strunk / Tibor Kiss
29
+ Text Bank (Suomen Kielen newspapers
30
+ Tekstipankki)
31
+ Finnish Center for IT Science
32
+ (CSC)
33
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
34
+ french.pickle French Multilingual Corpus 1 (ECI) Le Monde ~370,000 Jan Strunk / Tibor Kiss
35
+ (European)
36
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
37
+ german.pickle German Neue Zürcher Zeitung AG Neue Zürcher Zeitung ~847,000 Jan Strunk / Tibor Kiss
38
+ (Switzerland) CD-ROM
39
+ (Uses "ss"
40
+ instead of "ß")
41
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
42
+ greek.pickle Greek Efstathios Stamatatos To Vima (TO BHMA) ~227,000 Jan Strunk / Tibor Kiss
43
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
44
+ italian.pickle Italian Multilingual Corpus 1 (ECI) La Stampa, Il Mattino ~312,000 Jan Strunk / Tibor Kiss
45
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
46
+ norwegian.pickle Norwegian Centre for Humanities Bergens Tidende ~479,000 Jan Strunk / Tibor Kiss
47
+ (Bokmål and Information Technologies,
48
+ Nynorsk) Bergen
49
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
50
+ polish.pickle Polish Polish National Corpus Literature, newspapers, etc. ~1,000,000 Krzysztof Langner
51
+ (http://www.nkjp.pl/)
52
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
53
+ portuguese.pickle Portuguese CETENFolha Corpus Folha de São Paulo ~321,000 Jan Strunk / Tibor Kiss
54
+ (Brazilian) (Linguateca)
55
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
56
+ slovene.pickle Slovene TRACTOR Delo ~354,000 Jan Strunk / Tibor Kiss
57
+ Slovene Academy for Arts
58
+ and Sciences
59
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
60
+ spanish.pickle Spanish Multilingual Corpus 1 (ECI) Sur ~353,000 Jan Strunk / Tibor Kiss
61
+ (European)
62
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
63
+ swedish.pickle Swedish Multilingual Corpus 1 (ECI) Dagens Nyheter ~339,000 Jan Strunk / Tibor Kiss
64
+ (and some other texts)
65
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
66
+ turkish.pickle Turkish METU Turkish Corpus Milliyet ~333,000 Jan Strunk / Tibor Kiss
67
+ (Türkçe Derlem Projesi)
68
+ University of Ankara
69
+ -----------------------------------------------------------------------------------------------------------------------------------------------------------------------
70
+
71
+ The corpora contained about 400,000 tokens on average and mostly consisted of newspaper text converted to
72
+ Unicode using the codecs module.
73
+
74
+ Kiss, Tibor and Strunk, Jan (2006): Unsupervised Multilingual Sentence Boundary Detection.
75
+ Computational Linguistics 32: 485-525.
76
+
77
+ ---- Training Code ----
78
+
79
+ # import punkt
80
+ import nltk.tokenize.punkt
81
+
82
+ # Make a new Tokenizer
83
+ tokenizer = nltk.tokenize.punkt.PunktSentenceTokenizer()
84
+
85
+ # Read in training corpus (one example: Slovene)
86
+ import codecs
87
+ text = codecs.open("slovene.plain","Ur","iso-8859-2").read()
88
+
89
+ # Train tokenizer
90
+ tokenizer.train(text)
91
+
92
+ # Dump pickled tokenizer
93
+ import pickle
94
+ out = open("slovene.pickle","wb")
95
+ pickle.dump(tokenizer, out)
96
+ out.close()
97
+
98
+ ---------
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/abbrev_types.txt ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ t
2
+ množ
3
+ např
4
+ j.h
5
+ man
6
+ ú
7
+ jug
8
+ dr
9
+ bl
10
+ ml
11
+ okr
12
+ st
13
+ uh
14
+ šp
15
+ judr
16
+ u.s.a
17
+ p
18
+ arg
19
+ žitě
20
+ st.celsia
21
+ etc
22
+ p.s
23
+ t.r
24
+ lok
25
+ mil
26
+ ict
27
+ n
28
+ tl
29
+ min
30
+ č
31
+ d
32
+ al
33
+ ravenně
34
+ mj
35
+ nar
36
+ plk
37
+ s.p
38
+ a.g
39
+ roč
40
+ b
41
+ zdi
42
+ r.s.c
43
+ přek
44
+ m
45
+ gen
46
+ csc
47
+ mudr
48
+ vic
49
+ š
50
+ sb
51
+ resp
52
+ tzn
53
+ iv
54
+ s.r.o
55
+ mar
56
+ w
57
+ čs
58
+ vi
59
+ tzv
60
+ ul
61
+ pen
62
+ zv
63
+ str
64
+ čp
65
+ org
66
+ rak
67
+ sv
68
+ pplk
69
+ u.s
70
+ prof
71
+ c.k
72
+ op
73
+ g
74
+ vii
75
+ kr
76
+ ing
77
+ j.o
78
+ drsc
79
+ m3
80
+ l
81
+ tr
82
+ ceo
83
+ ch
84
+ fuk
85
+ vl
86
+ viii
87
+ líp
88
+ hl.m
89
+ t.zv
90
+ phdr
91
+ o.k
92
+ tis
93
+ doc
94
+ kl
95
+ ard
96
+ čkd
97
+ pok
98
+ apod
99
+ r
100
+
101
+ a.s
102
+ j
103
+ jr
104
+ i.m
105
+ e
106
+ kupř
107
+ f
108
+
109
+ xvi
110
+ mir
111
+ atď
112
+ vr
113
+ r.i.v
114
+ hl
115
+ kv
116
+ t.j
117
+ y
118
+ q.p.r
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/collocations.tab ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ i dejmala
2
+ ##number## prosince
3
+ h steina
4
+ ##number## listopadu
5
+ a dvořák
6
+ v klaus
7
+ i čnhl
8
+ ##number## wladyslawowo
9
+ ##number## letech
10
+ a jiráska
11
+ a dubček
12
+ ##number## štrasburk
13
+ ##number## juniorské
14
+ ##number## století
15
+ ##number## kola
16
+ ##number## pád
17
+ ##number## května
18
+ ##number## týdne
19
+ v dlouhý
20
+ k design
21
+ ##number## červenec
22
+ i ligy
23
+ ##number## kolo
24
+ z svěrák
25
+ ##number## mája
26
+ ##number## šimková
27
+ a bělého
28
+ a bradáč
29
+ ##number## ročníku
30
+ ##number## dubna
31
+ a vivaldiho
32
+ v mečiara
33
+ c carrićre
34
+ ##number## sjezd
35
+ ##number## výroční
36
+ ##number## kole
37
+ ##number## narozenin
38
+ k maleevová
39
+ i čnfl
40
+ ##number## pádě
41
+ ##number## září
42
+ ##number## výročí
43
+ a dvořáka
44
+ h g.
45
+ ##number## ledna
46
+ a dvorský
47
+ h měsíc
48
+ ##number## srpna
49
+ ##number## tř.
50
+ a mozarta
51
+ ##number## sudetoněmeckých
52
+ o sokolov
53
+ k škrach
54
+ v benda
55
+ ##number## symfonie
56
+ ##number## července
57
+ x šalda
58
+ c abrahama
59
+ a tichý
60
+ ##number## místo
61
+ k bielecki
62
+ v havel
63
+ ##number## etapu
64
+ a dubčeka
65
+ i liga
66
+ ##number## světový
67
+ v klausem
68
+ ##number## ženy
69
+ ##number## létech
70
+ ##number## minutě
71
+ ##number## listopadem
72
+ ##number## místě
73
+ o vlček
74
+ k peteraje
75
+ i sponzor
76
+ ##number## června
77
+ ##number## min.
78
+ ##number## oprávněnou
79
+ ##number## květnu
80
+ ##number## aktu
81
+ ##number## květnem
82
+ ##number## října
83
+ i rynda
84
+ ##number## února
85
+ i snfl
86
+ a mozart
87
+ z košler
88
+ a dvorskému
89
+ v marhoul
90
+ v mečiar
91
+ ##number## ročník
92
+ ##number## máje
93
+ v havla
94
+ k gott
95
+ s bacha
96
+ ##number## ad
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/czech/sent_starters.txt ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ milena
3
+ tomáš
4
+ oznámila
5
+ podle
6
+ my
7
+ vyplývá
8
+ hlavní
9
+ jelikož
10
+ musíme
11
+ kdyby
12
+ foto
13
+ rozptylové
14
+ snad
15
+ zároveň
16
+ jaroslav
17
+ po
18
+ v
19
+ kromě
20
+ pokud
21
+ toto
22
+ jenže
23
+ oba
24
+ jak
25
+ zatímco
26
+ ten
27
+ myslím
28
+ navíc
29
+ dušan
30
+ zdá
31
+ dnes
32
+ přesto
33
+ tato
34
+ ti
35
+ bratislava
36
+ ale
37
+ když
38
+ nicméně
39
+ tento
40
+ mirka
41
+ přitom
42
+ dokud
43
+ jan
44
+ bohužel
45
+ ta
46
+ díky
47
+ prohlásil
48
+ praha
49
+ jestliže
50
+ jde
51
+ vždyť
52
+ moskva
53
+ proto
54
+ to
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/abbrev_types.txt ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ t
2
+ tlf
3
+ b.p
4
+ evt
5
+ j.h
6
+ lenz
7
+ mht
8
+ gl
9
+ bl
10
+ stud.polit
11
+ e.j
12
+ st
13
+ o
14
+ dec
15
+ mag
16
+ h.b
17
+ p
18
+ adm
19
+ el.lign
20
+ e.s
21
+ saalba
22
+ styrt
23
+ nr
24
+ m.a.s.h
25
+ etc
26
+ pharm
27
+ hg
28
+ j.j
29
+ dj
30
+ mountainb
31
+ f.kr
32
+ h.r
33
+ cand.jur
34
+ sp
35
+ osv
36
+ s.g
37
+ ndr
38
+ inc
39
+ b.i.g
40
+ dk-sver
41
+ sl
42
+ v.s.o.d
43
+ cand.mag
44
+ d.v.s
45
+ v.i
46
+ bøddel
47
+ fr
48
+ ø«
49
+ dr.phil
50
+ chr
51
+ p.d
52
+ bj
53
+ fhv
54
+ tilskudsforhold
55
+ m.a
56
+ sek
57
+ p.g.a
58
+ int
59
+ pokalf
60
+ ik
61
+ dir
62
+ em-lodtrækn
63
+ a.h
64
+ o.lign
65
+ p.t
66
+ m.v
67
+ n.j
68
+ m.h.t
69
+ m.m
70
+ a.p
71
+ pers
72
+ 4-bakketurn
73
+ dr.med
74
+ w.ø
75
+ polit
76
+ fremsættes
77
+ techn
78
+ tidl
79
+ o.g
80
+ i.c.i
81
+ mill
82
+ skt
83
+ m.fl
84
+ cand.merc
85
+ kbh
86
+ indiv
87
+ stk
88
+ dk-maked
89
+ memorandum
90
+ mestersk
91
+ mag.art
92
+ kitzb
93
+ h
94
+ lic
95
+ fig
96
+ dressurst
97
+ sportsg
98
+ r.e.m
99
+ d.u.m
100
+ sct
101
+ kld
102
+ bl.a
103
+ hf
104
+ g.a
105
+ corp
106
+ w
107
+ konk
108
+ zoeterm
109
+ b.t
110
+ a.d
111
+ l.b
112
+ jf
113
+ s.b
114
+ kgl
115
+ ill
116
+ beck
117
+ tosset
118
+ afd
119
+ johs
120
+ pct
121
+ k.b
122
+ sv
123
+ verbalt
124
+ kgs
125
+ l.m.k
126
+ j.l
127
+ aus
128
+ superl
129
+ t.v
130
+ mia
131
+ kr
132
+ pr
133
+ præmien
134
+ j.b.s
135
+ j.o
136
+ o.s.v
137
+ edb-oplysninger
138
+ o.m.a
139
+ ca
140
+ 1b
141
+ f.eks
142
+ rens
143
+ ch
144
+ mr
145
+ schw
146
+ d.c
147
+ utraditionelt
148
+ idrætsgym
149
+ hhv
150
+ e.l
151
+ s.s
152
+ eks
153
+ f.o.m
154
+ dk-storbrit
155
+ dk-jugo
156
+ n.z
157
+ derivater
158
+ c
159
+ pt
160
+ vm-kval
161
+ kl
162
+ hr
163
+ cand
164
+ jur
165
+ sav
166
+ h.c
167
+ arab.-danm
168
+ d.a.d
169
+ fl
170
+ o.a
171
+ a.s
172
+ cand.polit
173
+ grundejerform
174
+ j
175
+ faglærte
176
+ cr
177
+ a.a
178
+ mou
179
+ f.r.i
180
+ årh
181
+ o.m.m
182
+ sve
183
+ c.a
184
+ engl
185
+ sikkerhedssystemerne
186
+ m.f
187
+ j.k
188
+ phil
189
+ f
190
+ vet
191
+ mio
192
+ k.e
193
+ m.k
194
+ atla
195
+ idrætsg
196
+ n.n
197
+ 4-bakketur
198
+ dvs
199
+ sdr
200
+ s.j
201
+ hol
202
+ s.h
203
+ pei
204
+ kbhvn
205
+ aa
206
+ m.g.i
207
+ fvt
208
+
209
+ b.c
210
+ th
211
+ lrs
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/collocations.tab ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## skak
2
+ ##number## speedway
3
+ ##number## rally
4
+ ##number## april
5
+ ##number## dm-fin
6
+ ##number## viceformand
7
+ m jensen
8
+ ##number## kano/kajak
9
+ ##number## bowling
10
+ ##number## dm-finale
11
+ ##number## årh.
12
+ ##number## januar
13
+ ##number## august
14
+ ##number## marathon
15
+ ##number## kamp
16
+ ##number## skihop
17
+ ##number## etage
18
+ ##number## tennis
19
+ ##number## cykling
20
+ e andersen
21
+ ##number## december
22
+ g h.
23
+ ##number## neb
24
+ ##number## sektion
25
+ ##number## afd.
26
+ ##number## klasse
27
+ ##number## trampolin
28
+ ##number## bordtennis
29
+ ##number## formel
30
+ ##number## århundredes
31
+ ##number## dm-semifin
32
+ ##number## heks
33
+ ##number## taekwondo
34
+ ##number## galop
35
+ ##number## basketball
36
+ ##number## dm
37
+ m skræl
38
+ ##number## trav
39
+ ##number## provins
40
+ ##number## triathlon
41
+ k axel
42
+ ##number## rugby
43
+ s h.
44
+ ##number## klaverkoncert
45
+ a p.
46
+ e løgstrup
47
+ k telefax
48
+ ##number## gyldendal
49
+ ##number## fodbold
50
+ e rosenfeldt
51
+ ##number## oktober
52
+ k o.
53
+ ##number## september
54
+ ##number## dec.
55
+ ##number## juledag
56
+ ##number## badminton
57
+ ##number## sejlsport
58
+ ##number## håndbold
59
+ r førsund
60
+ e jørgensen
61
+ d ##number##
62
+ k e
63
+ ##number## alp.ski
64
+ ##number## judo
65
+ ##number## roning
66
+ ##number## november
67
+ ##number## atletik
68
+ ##number## århundrede
69
+ ##number## ridning
70
+ ##number## marts
71
+ m andersen
72
+ d roosevelt
73
+ ##number## brydning
74
+ s kr.
75
+ ##number## runde
76
+ ##number## division
77
+ ##number## sal
78
+ ##number## boksning
79
+ ##number## minut
80
+ ##number## golf
81
+ ##number## juni
82
+ ##number## symfoni
83
+ ##number## hurtigløb
84
+ k jørgensen
85
+ ##number## jörgen
86
+ ##number## klasses
87
+ e jacobsen
88
+ k jensen
89
+ ##number## februar
90
+ k nielsen
91
+ ##number## volleyball
92
+ ##number## maj
93
+ ##number## verdenskrig
94
+ ##number## juli
95
+ ##number## ishockey
96
+ ##number## kunstskøjteløb
97
+ b jørgensen
98
+ ##number## gymnastik
99
+ ##number## svømning
100
+ ##number## tw
101
+ i pedersens
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/danish/sent_starters.txt ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ kronik
2
+ alligevel
3
+ de
4
+ først
5
+ derfor
6
+ vi
7
+ selv
8
+ hertil
9
+ sådan
10
+ dette
11
+ sport
12
+ man
13
+ foto
14
+ begge
15
+ tag
16
+ dertil
17
+ reuter
18
+ efter
19
+ endelig
20
+ ifølge
21
+ lad
22
+ når
23
+ det
24
+ desuden
25
+ nu
26
+ reuters
27
+ årsagen
28
+ tænk
29
+ samtidig
30
+ udover
31
+ men
32
+ endvidere
33
+ rør
34
+ rb
35
+ udstillingen
36
+ faktabox
37
+ reception
38
+ blandt
39
+ hvad
40
+ skær
41
+ lilot
42
+ derudover
43
+ da
44
+ tilsæt
45
+ denne
46
+ afp
47
+ her
48
+ hvis
49
+ hæld
50
+ problemet
51
+ dermed
52
+ jeg
53
+ grafik
54
+ anmeldelse
55
+ den
56
+ ebbe
57
+ resultatet
58
+ tværtimod
59
+ hans
60
+ måske
61
+ feature
62
+ tillæg
63
+ hun
64
+ han
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/abbrev_types.txt ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ m.j
2
+ t
3
+ ph
4
+ j.h
5
+ p.a.m
6
+ j.m
7
+ dr
8
+ st
9
+ j.b.m
10
+ p
11
+ nr
12
+ h.s
13
+ e.d
14
+ t.e
15
+ a.v
16
+ esb
17
+ s.z
18
+ drs
19
+ b.b
20
+ m.o
21
+ inc
22
+ n
23
+ pensioenfonds
24
+ s.v.p
25
+ bod
26
+ fr
27
+ pk
28
+ r.p
29
+ c.p.j
30
+ v.l.n.r
31
+ chr
32
+ m.v.d
33
+ int
34
+ o.m
35
+ j.v.d
36
+ u.o.m
37
+ f.c
38
+ k
39
+ bijgebracht
40
+ ontwaakte
41
+ m
42
+ j.w
43
+ a.l
44
+ a.v.d
45
+ s.v
46
+ s
47
+ j.d
48
+ binnengekomen
49
+ ds
50
+ schouwburg
51
+ b.v
52
+ h
53
+ a
54
+ j.a
55
+ aanvielen
56
+ h.g
57
+ p.f
58
+ j.l
59
+ mgr
60
+ c.j
61
+ blz
62
+ l.e.h
63
+ w.k
64
+ g
65
+ m.g
66
+ r.v.d
67
+ ing
68
+ v.d
69
+ c.q
70
+ l
71
+ h.p
72
+ mr
73
+ gesch
74
+ e.l
75
+ p.j
76
+ mm
77
+ j.g
78
+ j.f
79
+ c
80
+ f.m
81
+ jl
82
+ r
83
+ o.a
84
+ a.s
85
+ ir
86
+ v
87
+ j
88
+ jr
89
+ e
90
+ m.i.v
91
+ l.a
92
+ f.v.d
93
+ aansluit
94
+ c.c
95
+ a.m
96
+ f.o.j
97
+ m.b
98
+ y
99
+ th
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/collocations.tab ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## sotelo
2
+ ##number## clas
3
+ ##number## buckler
4
+ ##number## carrera
5
+ ##number## rmo
6
+ ##number## orioli
7
+ w baron
8
+ ##number## morales
9
+ ##number## snotselelaank
10
+ ##number## arcarons
11
+ ##number## cavandoli
12
+ ##number## pdm
13
+ ##number## helvetia
14
+ ##number## panasonic
15
+ ##number## motorola
16
+ w bruinsma
17
+ ##number## heer
18
+ ##number## lotus
19
+ ##number## banesto
20
+ ##number## magnaldi
21
+ w jense
22
+ w heuvelmans
23
+ w spatje
24
+ ##number## telekom
25
+ f kennedy
26
+ ##number## gatorade
27
+ ##number## mg-gb
28
+ ##number## once
29
+ ##number## peterhansel
30
+ ##number## ariostea
31
+ ##number## tvm
32
+ ##number## höl
33
+ ##number## castorama
34
+ ##number## tulip
35
+ b situatie
36
+ ##number## mas
37
+ ##number## lotto
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/dutch/sent_starters.txt ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ het
2
+ daardoor
3
+ de
4
+ er
5
+ hoewel
6
+ wat
7
+ urlings
8
+ na
9
+ ze
10
+ alleen
11
+ dat
12
+ ik
13
+ pijls
14
+ wie
15
+ daarna
16
+ foto
17
+ als
18
+ boer
19
+ hammes
20
+ verder
21
+ ook
22
+ evers
23
+ vandaar
24
+ toen
25
+ we
26
+ langenberg
27
+ naast
28
+ want
29
+ in
30
+ wij
31
+ zo
32
+ hendrikx
33
+ daar
34
+ crouzen
35
+ dit
36
+ daarnaast
37
+ anp
38
+ zij
39
+ behalve
40
+ waarom
41
+ daarom
42
+ bovendien
43
+ hij
44
+ daarbij
45
+ nee
46
+ volgens
47
+ daarmee
48
+ bukkems
49
+ dvnl
50
+ eén
51
+ pas
52
+ tijdens
53
+ vooral
54
+ maar
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txt ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ct
2
+ m.j
3
+ t
4
+ a.c
5
+ n.h
6
+ ms
7
+ p.a.m
8
+ dr
9
+ pa
10
+ p.m
11
+ u.k
12
+ st
13
+ dec
14
+ u.s.a
15
+ lt
16
+ g.k
17
+ adm
18
+ p
19
+ h.m
20
+ ga
21
+ tenn
22
+ yr
23
+ sen
24
+ n.c
25
+ j.j
26
+ d.h
27
+ s.g
28
+ inc
29
+ vs
30
+ s.p.a
31
+ a.t
32
+ n
33
+ feb
34
+ sr
35
+ jan
36
+ s.a.y
37
+ n.y
38
+ col
39
+ g.f
40
+ c.o.m.b
41
+ d
42
+ ft
43
+ va
44
+ r.k
45
+ e.f
46
+ chg
47
+ r.i
48
+ a.g
49
+ minn
50
+ a.h
51
+ k
52
+ n.j
53
+ m
54
+ l.f
55
+ f.j
56
+ gen
57
+ i.m.s
58
+ s.a
59
+ aug
60
+ j.p
61
+ okla
62
+ m.d.c
63
+ ltd
64
+ oct
65
+ s
66
+ vt
67
+ r.a
68
+ j.c
69
+ ariz
70
+ w.w
71
+ b.v
72
+ ore
73
+ h
74
+ w.r
75
+ e.h
76
+ mrs
77
+ cie
78
+ corp
79
+ w
80
+ n.v
81
+ a.d
82
+ r.j
83
+ ok
84
+ . .
85
+ e.m
86
+ w.c
87
+ ill
88
+ nov
89
+ u.s
90
+ prof
91
+ conn
92
+ u.s.s.r
93
+ mg
94
+ f.g
95
+ ph.d
96
+ g
97
+ calif
98
+ messrs
99
+ h.f
100
+ wash
101
+ tues
102
+ sw
103
+ bros
104
+ u.n
105
+ l
106
+ wis
107
+ mr
108
+ sep
109
+ d.c
110
+ ave
111
+ e.l
112
+ co
113
+ s.s
114
+ reps
115
+ c
116
+ r.t
117
+ h.c
118
+ r
119
+ wed
120
+ a.s
121
+ v
122
+ fla
123
+ jr
124
+ r.h
125
+ c.v
126
+ m.b.a
127
+ rep
128
+ a.a
129
+ e
130
+ c.i.t
131
+ l.a
132
+ b.f
133
+ j.b
134
+ d.w
135
+ j.k
136
+ ala
137
+ f
138
+ w.va
139
+ sept
140
+ mich
141
+ n.m
142
+ j.r
143
+ l.p
144
+ s.c
145
+ colo
146
+ fri
147
+ a.m
148
+ g.d
149
+ kan
150
+ maj
151
+ ky
152
+ a.m.e
153
+ n.d
154
+ t.j
155
+ cos
156
+ nev
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/collocations.tab ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## international
2
+ ##number## rj
3
+ ##number## commodities
4
+ ##number## cooper
5
+ b stewart
6
+ ##number## genentech
7
+ ##number## wedgestone
8
+ i toussie
9
+ ##number## pepper
10
+ j fialka
11
+ o ludcke
12
+ ##number## insider
13
+ ##number## aes
14
+ i magnin
15
+ ##number## credit
16
+ ##number## corrections
17
+ ##number## financing
18
+ ##number## henley
19
+ ##number## business
20
+ ##number## pay-fone
21
+ b wigton
22
+ b edelman
23
+ b levine
24
+ ##number## leisure
25
+ b smith
26
+ j walter
27
+ ##number## pegasus
28
+ ##number## dividend
29
+ j aron
30
+ ##number## review
31
+ ##number## abreast
32
+ ##number## who
33
+ ##number## letters
34
+ ##number## colgate
35
+ ##number## cbot
36
+ ##number## notable
37
+ ##number## zimmer
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/english/sent_starters.txt ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ most
2
+ he
3
+ since
4
+ so
5
+ both
6
+ these
7
+ it
8
+ nevertheless
9
+ this
10
+ indeed
11
+ however
12
+ instead
13
+ under
14
+ similarly
15
+ some
16
+ though
17
+ while
18
+ when
19
+ in
20
+ despite
21
+ although
22
+ nonetheless
23
+ thus
24
+ there
25
+ if
26
+ the
27
+ nor
28
+ separately
29
+ moreover
30
+ but
31
+ they
32
+ yet
33
+ many
34
+ according
35
+ sales
36
+ among
37
+ meanwhile
38
+ even
39
+ i
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/abbrev_types.txt ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ eos
2
+ c
3
+ a.d
4
+ t.a.s.s
5
+ e.t
6
+ päevapiltnikud
7
+ c.h
8
+ b.p
9
+ amm
10
+ ameerika-mees
11
+ n.-ö
12
+ cm
13
+ b
14
+ mhm
15
+ a.s
16
+ m.e
17
+ j.l
18
+ j
19
+ u.t
20
+ vm
21
+ g.u.n
22
+ hajutada
23
+ p.s
24
+ a.b
25
+ c.h.-r
26
+ i.q
27
+ gr
28
+ fido
29
+ pankurit
30
+ s.v
31
+ l.l
32
+ c.-h
33
+ m.h
34
+ h.l
35
+ m.k
36
+ j.r
37
+ t.k
38
+ k.h
39
+ 89/90
40
+ h
41
+ a
42
+ dost
43
+ v.k
44
+ e.q
45
+ t.j
46
+ m.b
47
+ d
48
+ p.k
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/collocations.tab ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## juuni
2
+ ##number## novembril
3
+ ##number## juulilt
4
+ r järve-vomm
5
+ ##number## mida
6
+ n liidu
7
+ ##number## milliseid
8
+ ##number## oktoobri
9
+ ##number## iidol
10
+ m e
11
+ ##number## klassist
12
+ ##number## millest
13
+ ##number## august
14
+ ##number## pariis
15
+ ##number## septembrist
16
+ ##number## oktoober
17
+ ##number## märtsini
18
+ ##number## kust
19
+ k mägi
20
+ ##number## detsembrist
21
+ ##number## jaanuari
22
+ ##number## epee
23
+ ##number## nimetage
24
+ ##number## novembrini
25
+ ##number## eluaasta
26
+ s mill
27
+ ##number## helsingi
28
+ ##number## jaanuarini
29
+ ##number## aastail
30
+ ##number## augustil
31
+ ##number## millise
32
+ ##number## juulist
33
+ ##number## mai
34
+ ##number## novembri
35
+ ##number## oktoobrist
36
+ ##number## juunini
37
+ ##number## septembriks
38
+ ##number## detsembril
39
+ p s
40
+ ##number## jaanuar
41
+ ##number## aastate
42
+ ##number## milline
43
+ ##number## kelle
44
+ ##number## jaanuaril
45
+ s stadnikov
46
+ ##number## aastaks
47
+ ##number## stockholm
48
+ ##number## suurim
49
+ ##number## aasta
50
+ ##number## sajandi
51
+ ##number## millega
52
+ ##number## aastast
53
+ ##number## aastal
54
+ ##number## kumb
55
+ ##number## septembril
56
+ ##number## korruselt
57
+ ##number## septembri
58
+ ##number## veebruarini
59
+ ##number## london
60
+ ##number## aastatel
61
+ ##number## september
62
+ ##number## veebruari
63
+ ##number## oktoobrini
64
+ ##number## mail
65
+ m kassovitz
66
+ ##number## action-film
67
+ ##number## mis
68
+ k herkül
69
+ n n
70
+ ##number## detsembrini
71
+ ##number## imre
72
+ t jõgeda
73
+ ##number## casino
74
+ ##number## septembrit
75
+ ##number## augustini
76
+ ##number## juulil
77
+ ##number## november
78
+ ##number## kuupäeval
79
+ ##number## taevas
80
+ ##number## septembrini
81
+ ##number## detsember
82
+ ##number## detsembri
83
+ ##number## juunil
84
+ ##number## augustist
85
+ n jurist
86
+ ##number## missugust
87
+ ##number## aastatesse
88
+ ##number## aprillil
89
+ ##number## augusti
90
+ ##number## oktoobril
91
+ ##number## märtsil
92
+ ##number## a
93
+ ##number## the
94
+ ##number## sajandil
95
+ ##number## aastani
96
+ ##number## juuli
97
+ ##number## septembrile
98
+ ##number## millist
99
+ ##number## millised
100
+ ##number## veebruaril
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/estonian/sent_starters.txt ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ kalad
2
+ õnneks
3
+ selle
4
+ maimu
5
+ teisipäeval
6
+ ma
7
+ skorpion
8
+ aga
9
+ lisaks
10
+ selleks
11
+ maitse
12
+ esiteks
13
+ erinevalt
14
+ pealegi
15
+ praegu
16
+ kas
17
+ tegelikult
18
+ neitsi
19
+ nädalavahetus
20
+ tema
21
+ kui
22
+ seega
23
+ täna
24
+ lugupidamisega
25
+ miks
26
+ teiseks
27
+ väldi
28
+ pohlak
29
+ osades
30
+ sõnn
31
+ samas
32
+ nimelt
33
+ juhtkiri
34
+ krimi
35
+ nädalavahetusel
36
+ näiteks
37
+ kuidas
38
+ ambur
39
+ telgmaa
40
+ laupäeval
41
+ seetõttu
42
+ rezhissöör
43
+ kahjuks
44
+ ent
45
+ samuti
46
+ ehkki
47
+ veevalaja
48
+ seepärast
49
+ muidugi
50
+ kuna
51
+ tänaseks
52
+ mina
53
+ loomulikult
54
+ ometi
55
+ arvamus
56
+ lõvi
57
+ ee
58
+ niisiis
59
+ mul
60
+ kaksikud
61
+ tõsi
62
+ hinnete
63
+ sestap
64
+ tõenäoliselt
65
+ samal
66
+ see
67
+ paraku
68
+ jäär
69
+ kokkuvõttes
70
+ küllap
71
+ muide
72
+ nüüd
73
+ kolmapäeval
74
+ võibolla
75
+ kuid
76
+ nädalavahetuse
77
+ kuigi
78
+ võid
79
+ lõpuks
80
+ kaalud
81
+ areen
82
+ kirjad
83
+ vähk
84
+ esmaspäeval
85
+ nii
86
+ need
87
+ uue
88
+ ta
89
+ minu
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/abbrev_types.txt ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ t
2
+ suom
3
+ dr
4
+ st
5
+ 970125090.jtun
6
+ p
7
+ sis
8
+ t.h
9
+ 961221327.jtun
10
+ a.i
11
+ milj
12
+ ski
13
+ kp
14
+ 970131067.jtun
15
+ 970124030.jtun
16
+ nk
17
+ va
18
+ pan
19
+ yhteystiedot
20
+ ruots
21
+ jne
22
+ t.a
23
+ l.-g
24
+ k
25
+ j.w
26
+ p2
27
+ oik
28
+ 970102248.jtun
29
+ hj
30
+ s
31
+ vt
32
+ muistelmia
33
+ o.s
34
+ elo
35
+ h
36
+ ortod
37
+ o.l
38
+ w
39
+ tms
40
+ 970120219.jtun
41
+ pj
42
+ ok
43
+ toissapäiväinen
44
+ 28.t1
45
+ pelintekijä
46
+ 970111011.jtun
47
+ op
48
+ os
49
+ ns
50
+ m.g
51
+ o.-i
52
+ m3
53
+ pros
54
+ mr
55
+ 970102171.jtun
56
+ waller
57
+ hels
58
+ rotary-järjestössä
59
+ ins
60
+ esim
61
+ apul
62
+ fil
63
+ id
64
+ ym
65
+ j
66
+ rf
67
+ v.o
68
+ lis
69
+ c.a
70
+ em
71
+ kand
72
+ r.y
73
+ valt
74
+ dipl
75
+ ö
76
+ 970111092.jtun
77
+ ponteva
78
+ y
79
+ kapakoista
80
+ 970130160.jtun
81
+ th
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/collocations.tab ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## sm
2
+ ##number## ohjelmassa
3
+ ##number## a3
4
+ ##number## rc3
5
+ ##number## rxd4
6
+ ##number## hxg4
7
+ o stenberg
8
+ ##number## lg5
9
+ ##number## tallitontun
10
+ ##number## lähetysohjeet
11
+ ##number## uimakoulu
12
+ ##number## jaana
13
+ ##number## alustuksen
14
+ ##number## uppo-nallen
15
+ ##number## anne
16
+ ##number## rxf3
17
+ a sjögren
18
+ ##number## kamarikuoro
19
+ ##number## vetäjänä
20
+ ##number## pääsymaksu
21
+ ##number## kerros
22
+ ##number## kurssi
23
+ ##number## kuori
24
+ ##number## g4
25
+ ##number## h3
26
+ ##number## tiede-teatterissa
27
+ ##number## kh2
28
+ ##number## kausimaksu
29
+ ##number## tia
30
+ ##number## gxf5
31
+ ##number## täky-galleria
32
+ ##number## le2
33
+ ##number## te8+
34
+ ##number## la4
35
+ ##number## keitä
36
+ ##number## huhtikuuta
37
+ ##number## menotiedoissa
38
+ ##number## valmista
39
+ ##number## txb5
40
+ ##number## maskeerauskurssin
41
+ ##number## rd2
42
+ ##number## re2
43
+ ##number## solisteina
44
+ ##number## esitelmä
45
+ ##number## puupiirrossarja
46
+ ##number## ta1
47
+ ##number## vaahdota
48
+ ##number## h4
49
+ ##number## kesäkuuta
50
+ ##number## liikkeitä
51
+ ##number## tuolloin
52
+ ##number## viikko
53
+ ##number## mittaa
54
+ a sjögrenin
55
+ ##number## exf6
56
+ ##number## rc6+
57
+ ##number## viimeistele
58
+ ##number## ld1
59
+ ##number## elokuuta
60
+ ##number## dh5+
61
+ ##number## syyskuuta
62
+ ##number## opettajina
63
+ ##number## b3
64
+ ##number## rauhankatu
65
+ c clarke
66
+ ##number## saakka
67
+ ##number## elokuvat
68
+ b huggins
69
+ g gahmberg
70
+ ##number## luento
71
+ ##number## lf3
72
+ ##number## tammikuuta
73
+ ##number## ryömä
74
+ ##number## meller
75
+ ##number## jäsenkortti
76
+ ##number## esiintyjinä
77
+ ##number## maria
78
+ ##number## lf4
79
+ ##number## siirto
80
+ ##number## aurinko
81
+ ##number## lxg6
82
+ ##number## marraskuuta
83
+ ##number## harjoituksissa
84
+ ##number## romantika-yhtye
85
+ ##number## g3
86
+ ##number## heinäkuuta
87
+ ##number## rxd5
88
+ ##number## kuumenna
89
+ e hämäläisen
90
+ ##number## bxc4
91
+ ##number## te1
92
+ ##number## kg2
93
+ ##number## osallistumismaksu
94
+ ##number## re5
95
+ ##number## ohjelma
96
+ ##number## varapuheenjohtajaksi
97
+ ##number## raisa
98
+ ##number## päivään
99
+ ##number## luokan
100
+ ##number## sulata
101
+ ##number## levitä
102
+ ##number## kaustinen
103
+ ##number## kuoroa
104
+ ##number## df3
105
+ v helsingistä
106
+ ##number## mieskuoro
107
+ ##number## lokakuuta
108
+ ##number## kerho
109
+ ##number## helmikuuta
110
+ ##number## kokkola
111
+ ##number## suuruusluokan
112
+ v kaupungista
113
+ ##number## krs
114
+ ##number## tekstit
115
+ ##number## menyy
116
+ ##number## rf3
117
+ ##number## ulkoasiainministeriön
118
+ ##number## kaada
119
+ ##number## cxd5
120
+ ##number## ilmailumuseo
121
+ e waris
122
+ ##number## kierros
123
+ ##number## tunnille
124
+ ##number## kh3
125
+ ##number## ohjaus
126
+ a t.
127
+ ##number## postimaksu
128
+ ##number## pane
129
+ ##number## th3
130
+ ##number## joulukuuta
131
+ ##number## vatkaa
132
+ ##number## kokeessa
133
+ l j.
134
+ ##number## asti
135
+ ##number## opastajana
136
+ ##number## kirsi
137
+ ##number## lc2
138
+ ##number## lh2
139
+ ##number## e4
140
+ ##number## sairaankuljetukset
141
+ ##number## sekoita
142
+ ##number## mervi
143
+ ##number## de2
144
+ a pietilän
145
+ ##number## kf1
146
+ ##number## toukokuuta
147
+ ##number## maaliskuuta
148
+ ##number## leikkaa
149
+ ##number## ryhmänäytökset
150
+ v maaseudulta
151
+ ##number## de3-e1
152
+ ##number## c4
153
+ ##number## ta1-b1
154
+ ##number## d5
155
+ ##number## pia
156
+ ##number## lxd6
157
+ ##number## d4
158
+ ##number## f3-f4
159
+ ##number## dxg6+
160
+ ##number## sari
161
+ ##number## pelkkään
162
+ ##number## ld3
163
+ ##number## perkaa
164
+ ##number## lg3
165
+ ##number## kg3
166
+ ##number## kvm
167
+ ##number## tb1xb6
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/finnish/sent_starters.txt ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ siinä
2
+ lämpötila
3
+ viiden
4
+ he
5
+ vapaa
6
+ viime
7
+ useimmat
8
+ kansallisooppera
9
+ rooleissa
10
+ näin
11
+ odotettavissa
12
+ tiedustelut
13
+ kansallisteatterin
14
+ sen
15
+ musiikki
16
+ monet
17
+ uusi
18
+ avoinna
19
+ pakkasta
20
+ freeze
21
+ tämä
22
+ lämpö
23
+ lautakunta
24
+ vastaväittäjänä
25
+ päivällä
26
+ tällä
27
+ esimerkiksi
28
+ varoituksia
29
+ merenkurkku
30
+ meriennuste
31
+ näyttelyssä
32
+ kun
33
+ pilvistä
34
+ silloin
35
+ selkämeren
36
+ suurin
37
+ se
38
+ jos
39
+ vaihtelevaa
40
+ vastaväittäjinä
41
+ sivu
42
+ kaupunginteatterin
43
+ pilvisyys
44
+ siellä
45
+ siksi
46
+ kurssimaksu
47
+ tämän
48
+ kotimaa
49
+ näiden
50
+ teatteri
51
+ kaikki
52
+ puolipilvistä
53
+ niiden
54
+ maksimilämpötila
55
+ lisäksi
56
+ kaupunginhallitus
57
+ helsingin
58
+ nyt
59
+ samalla
60
+ hänen
61
+ olen
62
+ kaupunkikierros
63
+ vastaväittäjä
64
+ ne
65
+ tästä
66
+ enimmäkseen
67
+ poika
68
+ niinpä
69
+ viirus
70
+ me
71
+ poliisi
72
+ liput
73
+ ilmoittautuminen
74
+ tarjoa
75
+ hän
76
+ molemmat
77
+ ulkomaat
78
+ rock
79
+ lääketieteen
80
+ tanssi
81
+ sainks
82
+ näyttely
83
+ lisätietoja
84
+ ulkomaiden
85
+ näyttelyn
86
+ palo
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/abbrev_types.txt ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ p.o.l
2
+ pds
3
+ 3o
4
+ inscr
5
+ suè
6
+ z
7
+ abst
8
+ g.-b
9
+ tél
10
+ r
11
+ ed
12
+ o
13
+ b
14
+ esp
15
+ j.l
16
+ v
17
+ k
18
+ e.p
19
+ aus
20
+ jap
21
+ r.e
22
+ gb-bel
23
+ p
24
+ aut
25
+ usx
26
+ arg
27
+ g
28
+ e
29
+ etc
30
+ fra
31
+ p.s
32
+ j.-l
33
+ blu
34
+ e.-u
35
+ f.b
36
+ msf
37
+ e.d
38
+ shi
39
+ can
40
+ j.b
41
+ s.a
42
+ f.o
43
+ you
44
+ mir
45
+ inc
46
+ ital
47
+ expr
48
+ tch
49
+ g-b-bel
50
+ cid
51
+ c.u
52
+ ctk
53
+ j.-m.g
54
+ bta
55
+ p.-b
56
+ cie
57
+ ita
58
+ equ
59
+ corp
60
+ vot
61
+ w
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/collocations.tab ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## shinozuka-magne
2
+ ##number## ambrosino-baumgartner
3
+ c tanvier
4
+ f b.
5
+ ##number## waldegaard-fenouil
6
+ ##number## fermé
7
+ a dechaume
8
+ i demongeot
9
+ s motos
10
+ ##number## rahier
11
+ ##number## magnaldi
12
+ ##number## orioli
13
+ f tél.
14
+ ##number## cowan-delferrier
15
+ ##number## vatanen-berglund
16
+ ##number## picco
17
+ ##number## masuoka-oligo
18
+ ##number## medardo
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/french/sent_starters.txt ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ c
2
+ depuis
3
+ la
4
+ enfin
5
+ certains
6
+ selon
7
+ cet
8
+ car
9
+ ces
10
+ il
11
+ cependant
12
+ pour
13
+ j
14
+ alors
15
+ un
16
+ certes
17
+ les
18
+ nous
19
+ dans
20
+ le
21
+ une
22
+ si
23
+ mais
24
+ en
25
+ dès
26
+ or
27
+ tout
28
+ ils
29
+ l
30
+ mr
31
+ malgré
32
+ elles
33
+
34
+ je
35
+ on
36
+ quand
37
+ pourtant
38
+ cela
39
+ a
40
+ après
41
+ puis
42
+ ce
43
+ elle
44
+ voilà
45
+ cette
46
+ comment
47
+ quant
48
+ ainsi
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/abbrev_types.txt ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ rfr
2
+ t
3
+ c
4
+ a.d
5
+ dk
6
+ he
7
+ mjm
8
+ inkl
9
+ bt
10
+ 69f
11
+ crz
12
+ dr
13
+ st
14
+ ib
15
+ liv
16
+ mrd
17
+ n.r
18
+ rg
19
+ v
20
+ vgl
21
+ mgr
22
+ cs
23
+ prof
24
+ j
25
+ kfr
26
+ bd
27
+ fre
28
+ gfh
29
+ fon
30
+ m
31
+ rp
32
+ nr
33
+ chr
34
+ etc
35
+ hg
36
+ sx
37
+ rz
38
+ 48f
39
+ kmu
40
+ abs
41
+ nkm
42
+ z.b
43
+ usw
44
+ f
45
+ d.h
46
+ lz
47
+ sc
48
+ usf
49
+ gir
50
+ hag
51
+ ff
52
+ mio
53
+ zr
54
+ k
55
+ h
56
+ mey
57
+ bst
58
+ ne
59
+ u.a
60
+ fem
61
+ bzw
62
+
63
+ med
64
+ u
65
+ lts
66
+ fr
67
+ s.o.s
68
+ w
69
+ lib
70
+ k.a
71
+ th
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/collocations.tab ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##number## oktober
2
+ ##number## jahrhunderts
3
+ ##number## geburtstag
4
+ ##number## juni
5
+ s ##number##
6
+ ##number## september
7
+ ##number## mai
8
+ ##number## dezember
9
+ ##number## april
10
+ ##number## ahv-revision
11
+ ##number## revision
12
+ ##number## jahrhundert
13
+ ##number## landwirtschaftsbericht
14
+ ##number## altersjahr
15
+ ##number## februar
16
+ a schumpeter
17
+ ##number## freiheit
18
+ ##number## august
19
+ ##number## januar
20
+ ##number## märz
21
+ a meyers
22
+ ##number## november
23
+ ##number## bauetappe
24
+ ##number## ahv-
25
+ ##number## eu-richtlinie
26
+ ##number## juli
27
+ a meyer
28
+ ##number## säule
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/german/sent_starters.txt ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ das
2
+ man
3
+ es
4
+ wir
5
+ dabei
6
+ ferner
7
+ ähnliches
8
+ während
9
+ entscheidend
10
+ ausserdem
11
+ ein
12
+ in
13
+ der
14
+ daraus
15
+ obschon
16
+ beide
17
+ hier
18
+ all
19
+ neben
20
+ solche
21
+ hingegen
22
+ selbstverständlich
23
+ daneben
24
+ hinzu
25
+ vielmehr
26
+ sie
27
+ natürlich
28
+ obwohl
29
+ nun
30
+ doch
31
+ ob
32
+ abgesehen
33
+ überdies
34
+ im
35
+ zweitens
36
+ darin
37
+ erstens
38
+ dieses
39
+ nach
40
+ wer
41
+ da
42
+ interessant
43
+ seit
44
+ zudem
45
+ darüber
46
+ umgekehrt
47
+ ähnlich
48
+ aber
49
+ was
50
+ nachdem
51
+ insbesondere
52
+ statt
53
+ angesichts
54
+ gefragt
55
+ gleiches
56
+ solange
57
+ wenn
58
+ dies
59
+ dass
60
+ wie
61
+ damit
62
+ allerdings
63
+ denn
64
+ letztere
65
+ eine
66
+ selbst
67
+ gleichzeitig
68
+ wo
69
+ weder
70
+ gerade
71
+ unter
72
+ problematischer
73
+ wieso
74
+ dennoch
75
+ bei
76
+ deshalb
77
+ davon
78
+ andernfalls
79
+ er
80
+ die
81
+ anders
82
+ auch
83
+ ebenso
84
+ so
85
+ inzwischen
86
+ sonst
87
+ immerhin
88
+ entsprechend
89
+ danach
90
+ am
91
+ trotz
92
+ trotzdem
93
+ worum
94
+ damals
95
+ dafür
96
+ schliesslich
97
+ gemäss
98
+ demgegenüber
99
+ warum
100
+ letzteres
101
+ mit
102
+ dazu
103
+ anderseits
104
+ ganz
105
+ zwar
106
+ dieser
107
+ diese
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/abbrev_types.txt ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ κλ
2
+ δημ
3
+ χλμ
4
+ σ.τ.ε
5
+ ό.π
6
+ δρχ
7
+ κων
8
+ χρ
9
+ π.α
10
+ ριχ
11
+ π.χρ
12
+ υγ
13
+ tel
14
+ ζ
15
+ ο.π
16
+ βασ
17
+ γλ
18
+ n.c
19
+ d.j
20
+ σωκ
21
+ π
22
+ ιω
23
+ αχ
24
+ βα
25
+ γερ
26
+ εκδ
27
+ κλπ
28
+ φ
29
+ ελ
30
+ οσ
31
+ α
32
+ σελ
33
+ ευ
34
+ ε.έ
35
+ ρ
36
+ ε.τ.α
37
+ λ
38
+ εβ
39
+ θρ
40
+ ν
41
+ βλ
42
+ ηλ
43
+ γ
44
+ αρ
45
+ π.χ
46
+ ε.μ
47
+ κ.μ
48
+ α.ε
49
+ μιχ
50
+ δισ
51
+ ολ
52
+ μ
53
+ κ.ά
54
+ κ
55
+ δηλ
56
+ ε.α.χ
57
+ πρ
58
+ αγ
59
+ μac
60
+ κ.ο.κ
61
+ λ.χ
62
+ θ
63
+ αδσ
64
+ εκατ
65
+ δρη
66
+ εμμ
67
+ δ
68
+ δεκ
69
+ σ.σ
70
+ 55ο
71
+ κκ
72
+ αδ
73
+ τ.μ
74
+ ε.ε
75
+ μ.χ
76
+ ν.μ
77
+ κτλ
78
+ δολ
79
+ κ.ά.π
80
+ αγγ
81
+ μ.κ
82
+ δ.σ
83
+ μπ
84
+ έκδ
85
+ ι
86
+ v
87
+ χαρ
88
+ γρ
89
+ μ.μ.ε
90
+ σχ
91
+ λεκ
92
+ σπ
93
+ πλι
94
+ αθ
95
+ χ
96
+ τζ
97
+ τρισ
98
+ στ
99
+ ευθ
100
+ μ.μ
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/collocations.tab ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ β δερτιλής
2
+ ##number## φιλάρετος
3
+ ο gehry
4
+ η αβεε
5
+ ##number## βλ.
6
+ β παπανδρέου
7
+ σ μ.
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/greek/sent_starters.txt ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ οπως
2
+ πάντως
3
+ δεύτερον
4
+ παράλληλα
5
+ οχι
6
+ ειδικότερα
7
+ τι
8
+ επίσης
9
+ ωστόσο
10
+ ενας
11
+ ηδη
12
+ σύμφωνα
13
+ συγκεκριμένα
14
+ ηταν
15
+ εκεί
16
+ αλλωστε
17
+ πολλοί
18
+ διότι
19
+ οποιος
20
+ τρίτον
21
+ πώς
22
+ ολοι
23
+ ισως
24
+ ο
25
+ ολες
26
+ οι
27
+ γιατί
28
+ αλλοι
29
+ οσοι
30
+ αυτό
31
+ τα
32
+ ολα
33
+ ετσι
34
+ ενα
35
+ πράγματι
36
+ αλλά
37
+ επιπλέον
38
+ δεν
39
+ εχει
40
+ αντίθετα
41
+ οσον
42
+ γι
43
+ αντιθέτως
44
+ ας
45
+ η
46
+ πρόκειται
47
+ αρα
48
+ οσο
49
+ αν
50
+ μετά
51
+ εξάλλου
52
+ το
53
+ οταν
54
+ πέρα
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/abbrev_types.txt ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ t
2
+ b.p
3
+ cer
4
+ sik
5
+ 'ing
6
+ dr
7
+ p.m
8
+ st
9
+ t.t.c
10
+ a.r
11
+ p
12
+ ecc
13
+ t.b
14
+ tel
15
+ etc
16
+ 'on
17
+ mb
18
+ g.dol
19
+ g.d.g
20
+ sè»
21
+ m.p
22
+ b.b
23
+ vs
24
+ s.p.a
25
+ g.b
26
+ v6
27
+ ipp
28
+ s.r
29
+ r.c
30
+ moz
31
+ n.f
32
+ s.mr
33
+ c.s
34
+ g.i.p
35
+ r.i
36
+ a.g
37
+ rc
38
+ 'è»
39
+ 1-o
40
+ e.p
41
+ m.g.b
42
+ gen
43
+ i.e
44
+ s.a
45
+ vic
46
+ g.gi
47
+
48
+ m.cas
49
+ re.po
50
+ giri/min
51
+ e.i
52
+ mrs
53
+ w
54
+ n.d.r
55
+ l4ª
56
+ bad
57
+ p.l.f
58
+ dur
59
+ s.l
60
+ t.s
61
+ wwf
62
+ u.q
63
+ lod
64
+ b.col
65
+ prof
66
+ n.s
67
+ ii.dd
68
+ a.f
69
+ c.i
70
+ op
71
+ end
72
+ g
73
+ 'u.s
74
+ o.b
75
+ t.t
76
+ s.m
77
+ ing
78
+ shi
79
+ oren
80
+ m.l
81
+ f.l.l
82
+ mr
83
+ jvp
84
+ fia
85
+ pag
86
+ e.c
87
+ g.p
88
+ pp
89
+ u
90
+ p.d.v
91
+ c.cer
92
+ cod
93
+ d.p.r
94
+ e.t
95
+ e.st
96
+ h.c
97
+ z
98
+ r
99
+ c.n.r
100
+ o.r
101
+ mons
102
+ j
103
+ jr
104
+ kin
105
+ v6»
106
+ g.p.s
107
+ l.z
108
+ c.a
109
+ m.f
110
+ sig
111
+ s.r.l
112
+ riz
113
+ f
114
+ m.s
115
+ c.c
116
+ l.p
117
+ f.ama
118
+ pi
119
+ s.c
120
+ p.d.p
121
+ ta
122
+ di»
123
+ r.e.s
124
+ n.d
125
+ p2»
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/collocations.tab ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ n ##number##
2
+ s pietro
3
+ s francisco
4
+ c wolf
5
+ s maria
6
+ a r.
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/ortho_context.tab ADDED
The diff for this file is too large to render. See raw diff
 
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/italian/sent_starters.txt ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ poi
2
+ c
3
+ la
4
+ temperatura
5
+ oggi
6
+ ebbene
7
+ infine
8
+ ieri
9
+ ecco
10
+ il
11
+ questo
12
+ quando
13
+ se
14
+ anche
15
+ e
16
+ ma
17
+ perciò
18
+ in
19
+ visibilità
20
+ gli
21
+ insomma
22
+ le
23
+ nel
24
+ lo
25
+ ora
26
+ adesso
27
+ venti
28
+ l
29
+ ci
30
+ per
31
+ inoltre
32
+ ho
33
+ secondo
34
+ non
35
+ così
36
+ intanto
37
+ certo
38
+ dopo
39
+ i
40
+ eppure
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/norwegian/abbrev_types.txt ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ t
2
+ p.p
3
+ bk
4
+ cc
5
+ pga
6
+ e.e.o
7
+ o.h
8
+ dr
9
+ st
10
+ uh
11
+ kk
12
+ t.d
13
+ h.m
14
+ p
15
+ adm
16
+ nr
17
+ etc
18
+ t.h
19
+ dæhlie-triumf
20
+ ev
21
+ udv
22
+ anm
23
+ ø
24
+ osv
25
+ dm
26
+ hi
27
+ b.b
28
+ inc
29
+ r.c
30
+ d.v.s
31
+ ce
32
+ fr
33
+ chr
34
+ adm.dir
35
+ m.a
36
+ b
37
+ p.t
38
+ m.v
39
+ k
40
+ m.m
41
+ i.l
42
+ mill
43
+ h.e
44
+ d.å
45
+ bl.a
46
+ i.h.h.t
47
+ mrs
48
+ b.i.t
49
+ sam.pol
50
+ o.l
51
+ w
52
+ jfr
53
+ h.g
54
+ str
55
+ mil.org
56
+ c.j
57
+ sifre
58
+ l.t
59
+ t.v
60
+ ex
61
+ gj.v
62
+ pr
63
+ d.y
64
+ j.o
65
+ g.c
66
+ avd
67
+ o.s.v
68
+ pol
69
+ ca
70
+ f.eks
71
+ tjenesteforsømmelse
72
+ mr
73
+ d.c
74
+ sam
75
+ .e
76
+ h.h.v
77
+ f.v
78
+ fenomen
79
+ kl
80
+ hr
81
+ c.h
82
+ miljøvernavdelingen
83
+ h.c
84
+ startstreken
85
+ r
86
+ o.a
87
+ mrd
88
+ a.s
89
+ j.v
90
+ j
91
+ jr
92
+ f.w
93
+ kfr
94
+ l.h
95
+ bås
96
+ schlickernrieder
97
+ f.-eks
98
+ f
99
+ 5.n7
100
+ c.c
101
+ fung
102
+ dvs
103
+ d.e
104
+ wc
105
+ f.å
106
+ th
Cosmos-Guardrail1/blocklist/nltk_data/tokenizers/punkt_tab/norwegian/collocations.tab ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ m skjærstad
2
+ ##number## plass
3
+ ##number## omgang
4
+ ##number## oktober
5
+ h rowe
6
+ ##number## juni
7
+ ##number## september
8
+ ##number## klasse
9
+ ##number## mai
10
+ ##number## april
11
+ ##number## nyttårsdag
12
+ d hillgaar
13
+ ##number## etasje
14
+ c sundts
15
+ o henrik
16
+ a himle
17
+ a robinson
18
+ m bjelland
19
+ ##number## d.å.
20
+ ##number## runden
21
+ h spang
22
+ ##number## etappen
23
+ ##number## mars-tog
24
+ ##number## februar
25
+ ##number## divisjonslaget
26
+ ##number## minutt
27
+ g larsen
28
+ ##number## divisjon
29
+ ##number## januar
30
+ ##number## august
31
+ m pedersen
32
+ m lillebø
33
+ ##number## november
34
+ h reimers
35
+ a hoffman
36
+ ##number## jubileumsår
37
+ ##number## desember
38
+ d hagesæther
39
+ ##number## divisjonsnivå
40
+ ##number## omgangen
41
+ n kristiansen
42
+ ##number## skaff
43
+ ##number## divisjonslag
44
+ a pettersen
45
+ ##number## divisjonskamper
46
+ ##number## plassen
47
+ ##number## juli
48
+ c sjaastad
49
+ ##number## runde
50
+ ##number## viseformann
51
+ i eliassen
52
+ ##number## mars
53
+ ##number## nurmis
54
+ i hagen