├── .gitignore ├── LICENSE └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | # Created by https://www.toptal.com/developers/gitignore/api/python,intellij,pycharm+iml,pycharm,vscode 2 | # Edit at https://www.toptal.com/developers/gitignore?templates=python,intellij,pycharm+iml,pycharm,vscode 3 | 4 | ### Intellij ### 5 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider 6 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 7 | 8 | # User-specific stuff 9 | .idea/**/workspace.xml 10 | .idea/**/tasks.xml 11 | .idea/**/usage.statistics.xml 12 | .idea/**/dictionaries 13 | .idea/**/shelf 14 | 15 | # Generated files 16 | .idea/**/contentModel.xml 17 | 18 | # Sensitive or high-churn files 19 | .idea/**/dataSources/ 20 | .idea/**/dataSources.ids 21 | .idea/**/dataSources.local.xml 22 | .idea/**/sqlDataSources.xml 23 | .idea/**/dynamic.xml 24 | .idea/**/uiDesigner.xml 25 | .idea/**/dbnavigator.xml 26 | 27 | # Gradle 28 | .idea/**/gradle.xml 29 | .idea/**/libraries 30 | 31 | # Gradle and Maven with auto-import 32 | # When using Gradle or Maven with auto-import, you should exclude module files, 33 | # since they will be recreated, and may cause churn. Uncomment if using 34 | # auto-import. 35 | # .idea/artifacts 36 | # .idea/compiler.xml 37 | # .idea/jarRepositories.xml 38 | # .idea/modules.xml 39 | # .idea/*.iml 40 | # .idea/modules 41 | # *.iml 42 | # *.ipr 43 | 44 | # CMake 45 | cmake-build-*/ 46 | 47 | # Mongo Explorer plugin 48 | .idea/**/mongoSettings.xml 49 | 50 | # File-based project format 51 | *.iws 52 | 53 | # IntelliJ 54 | out/ 55 | 56 | # mpeltonen/sbt-idea plugin 57 | .idea_modules/ 58 | 59 | # JIRA plugin 60 | atlassian-ide-plugin.xml 61 | 62 | # Cursive Clojure plugin 63 | .idea/replstate.xml 64 | 65 | # Crashlytics plugin (for Android Studio and IntelliJ) 66 | com_crashlytics_export_strings.xml 67 | crashlytics.properties 68 | crashlytics-build.properties 69 | fabric.properties 70 | 71 | # Editor-based Rest Client 72 | .idea/httpRequests 73 | 74 | # Android studio 3.1+ serialized cache file 75 | .idea/caches/build_file_checksums.ser 76 | 77 | ### Intellij Patch ### 78 | # Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721 79 | 80 | # *.iml 81 | # modules.xml 82 | # .idea/misc.xml 83 | # *.ipr 84 | 85 | # Sonarlint plugin 86 | # https://plugins.jetbrains.com/plugin/7973-sonarlint 87 | .idea/**/sonarlint/ 88 | 89 | # SonarQube Plugin 90 | # https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin 91 | .idea/**/sonarIssues.xml 92 | 93 | # Markdown Navigator plugin 94 | # https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced 95 | .idea/**/markdown-navigator.xml 96 | .idea/**/markdown-navigator-enh.xml 97 | .idea/**/markdown-navigator/ 98 | 99 | # Cache file creation bug 100 | # See https://youtrack.jetbrains.com/issue/JBR-2257 101 | .idea/$CACHE_FILE$ 102 | 103 | # CodeStream plugin 104 | # https://plugins.jetbrains.com/plugin/12206-codestream 105 | .idea/codestream.xml 106 | 107 | ### PyCharm ### 108 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider 109 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 110 | 111 | # User-specific stuff 112 | 113 | # Generated files 114 | 115 | # Sensitive or high-churn files 116 | 117 | # Gradle 118 | 119 | # Gradle and Maven with auto-import 120 | # When using Gradle or Maven with auto-import, you should exclude module files, 121 | # since they will be recreated, and may cause churn. Uncomment if using 122 | # auto-import. 123 | # .idea/artifacts 124 | # .idea/compiler.xml 125 | # .idea/jarRepositories.xml 126 | # .idea/modules.xml 127 | # .idea/*.iml 128 | # .idea/modules 129 | # *.iml 130 | # *.ipr 131 | 132 | # CMake 133 | 134 | # Mongo Explorer plugin 135 | 136 | # File-based project format 137 | 138 | # IntelliJ 139 | 140 | # mpeltonen/sbt-idea plugin 141 | 142 | # JIRA plugin 143 | 144 | # Cursive Clojure plugin 145 | 146 | # Crashlytics plugin (for Android Studio and IntelliJ) 147 | 148 | # Editor-based Rest Client 149 | 150 | # Android studio 3.1+ serialized cache file 151 | 152 | ### PyCharm Patch ### 153 | # Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721 154 | 155 | # *.iml 156 | # modules.xml 157 | # .idea/misc.xml 158 | # *.ipr 159 | 160 | # Sonarlint plugin 161 | # https://plugins.jetbrains.com/plugin/7973-sonarlint 162 | 163 | # SonarQube Plugin 164 | # https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin 165 | 166 | # Markdown Navigator plugin 167 | # https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced 168 | 169 | # Cache file creation bug 170 | # See https://youtrack.jetbrains.com/issue/JBR-2257 171 | 172 | # CodeStream plugin 173 | # https://plugins.jetbrains.com/plugin/12206-codestream 174 | 175 | ### PyCharm+iml ### 176 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider 177 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 178 | 179 | # User-specific stuff 180 | 181 | # Generated files 182 | 183 | # Sensitive or high-churn files 184 | 185 | # Gradle 186 | 187 | # Gradle and Maven with auto-import 188 | # When using Gradle or Maven with auto-import, you should exclude module files, 189 | # since they will be recreated, and may cause churn. Uncomment if using 190 | # auto-import. 191 | # .idea/artifacts 192 | # .idea/compiler.xml 193 | # .idea/jarRepositories.xml 194 | # .idea/modules.xml 195 | # .idea/*.iml 196 | # .idea/modules 197 | # *.iml 198 | # *.ipr 199 | 200 | # CMake 201 | 202 | # Mongo Explorer plugin 203 | 204 | # File-based project format 205 | 206 | # IntelliJ 207 | 208 | # mpeltonen/sbt-idea plugin 209 | 210 | # JIRA plugin 211 | 212 | # Cursive Clojure plugin 213 | 214 | # Crashlytics plugin (for Android Studio and IntelliJ) 215 | 216 | # Editor-based Rest Client 217 | 218 | # Android studio 3.1+ serialized cache file 219 | 220 | ### PyCharm+iml Patch ### 221 | # Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023 222 | 223 | *.iml 224 | modules.xml 225 | .idea/misc.xml 226 | *.ipr 227 | 228 | ### Python ### 229 | # Byte-compiled / optimized / DLL files 230 | __pycache__/ 231 | *.py[cod] 232 | *$py.class 233 | 234 | # C extensions 235 | *.so 236 | 237 | # Distribution / packaging 238 | .Python 239 | build/ 240 | develop-eggs/ 241 | dist/ 242 | downloads/ 243 | eggs/ 244 | .eggs/ 245 | lib/ 246 | lib64/ 247 | parts/ 248 | sdist/ 249 | var/ 250 | wheels/ 251 | pip-wheel-metadata/ 252 | share/python-wheels/ 253 | *.egg-info/ 254 | .installed.cfg 255 | *.egg 256 | MANIFEST 257 | 258 | # PyInstaller 259 | # Usually these files are written by a python script from a template 260 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 261 | *.manifest 262 | *.spec 263 | 264 | # Installer logs 265 | pip-log.txt 266 | pip-delete-this-directory.txt 267 | 268 | # Unit test / coverage reports 269 | htmlcov/ 270 | .tox/ 271 | .nox/ 272 | .coverage 273 | .coverage.* 274 | .cache 275 | nosetests.xml 276 | coverage.xml 277 | *.cover 278 | *.py,cover 279 | .hypothesis/ 280 | .pytest_cache/ 281 | pytestdebug.log 282 | 283 | # Translations 284 | *.mo 285 | *.pot 286 | 287 | # Django stuff: 288 | *.log 289 | local_settings.py 290 | db.sqlite3 291 | db.sqlite3-journal 292 | 293 | # Flask stuff: 294 | instance/ 295 | .webassets-cache 296 | 297 | # Scrapy stuff: 298 | .scrapy 299 | 300 | # Sphinx documentation 301 | docs/_build/ 302 | doc/_build/ 303 | 304 | # PyBuilder 305 | target/ 306 | 307 | # Jupyter Notebook 308 | .ipynb_checkpoints 309 | 310 | # IPython 311 | profile_default/ 312 | ipython_config.py 313 | 314 | # pyenv 315 | .python-version 316 | 317 | # pipenv 318 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 319 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 320 | # having no cross.py-platform support, pipenv may install dependencies that don't work, or not 321 | # install all needed dependencies. 322 | #Pipfile.lock 323 | 324 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 325 | __pypackages__/ 326 | 327 | # Celery stuff 328 | celerybeat-schedule 329 | celerybeat.pid 330 | 331 | # SageMath parsed files 332 | *.sage.py 333 | 334 | # Environments 335 | .env 336 | .venv 337 | env/ 338 | venv/ 339 | ENV/ 340 | env.bak/ 341 | venv.bak/ 342 | pythonenv* 343 | 344 | # Spyder project settings 345 | .spyderproject 346 | .spyproject 347 | 348 | # Rope project settings 349 | .ropeproject 350 | 351 | # mkdocs documentation 352 | /site 353 | 354 | # mypy 355 | .mypy_cache/ 356 | .dmypy.json 357 | dmypy.json 358 | 359 | # Pyre type checker 360 | .pyre/ 361 | 362 | # pytype static type analyzer 363 | .pytype/ 364 | 365 | # profiling data 366 | .prof 367 | 368 | ### vscode ### 369 | .vscode/* 370 | !.vscode/settings.json 371 | !.vscode/tasks.json 372 | !.vscode/launch.json 373 | !.vscode/extensions.json 374 | *.code-workspace 375 | .idea 376 | 377 | .DS_Store 378 | ._.DS_Store 379 | **/.DS_Store 380 | **/._.DS_Store 381 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Polyglot: Large Language Models of Well-balanced Competence in Multi-languages 2 | 3 | ## 1. Introduction 4 | 5 | ### Why another multilingual model? 6 | Various multilingual models such as [mBERT](https://huggingface.co/bert-base-multilingual-cased), [BLOOM](https://huggingface.co/bigscience/bloom), and [XGLM](https://arxiv.org/abs/2112.10668) have been released. 7 | Therefore, someone might ask, "why do we need to make multilingual models again?" Before answering the question, we would like to ask, "Why do people around the world make monolingual models in their language even though there are already many multilingual models?" We would like to point out there is a dissatisfaction with the non-English language performance of the current multilingual models as one of the most significant reason. So we want to make multilingual models with higher non-English language performance. This is the reason we need to make multilingual models again and why we name them ['Polyglot'](https://www.spanish.academy/blog/what-is-the-difference-between-a-polyglot-and-a-multilingual-person/). 8 | 9 | ## 2. Projects 10 | 11 | ### 1) Polyglot-Ko 12 | When we started our research, we have already had 1.2TB of Korean data collected by [TUNiB](https://tunib.ai/). Before we collected a large amount of multilingual data, we decided to try Korean modeling with the dataset we already had. This Korean model can be used for performance comparison with the multilingual models, and this model itself would help many Korean companies and researchers. 13 | 14 | | Size | Training Status | Model Card | Model Checkpoints | 15 | |:----:|:------------------------------------------------------------------------------------------:|:---------------------------------------------------------------:|:-------------------------------------------------------------------------:| 16 | | 1.3B | [Finished](https://wandb.ai/eleutherai/polyglot-ko/groups/polyglot-ko-1.3B) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-1.3b/tree/main) | 17 | | 3.8B | [Finished](https://wandb.ai/eleutherai/polyglot-ko/groups/polyglot-ko-3.8B) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-3.8b/tree/main) | 18 | | 5.8B | [Finished](https://wandb.ai/eleutherai/polyglot-ko/groups/polyglot-ko-5.8B) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-5.8b/tree/main) | 19 | |12.8B | [Finished](https://wandb.ai/eleutherai-oslo/polyglot-ko-12_8b) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | [Available](https://huggingface.co/EleutherAI/polyglot-ko-12.8b/tree/main) 20 | 21 | - Technical report: https://arxiv.org/abs/2306.02254 22 | - Contributors: [Hyunwoong Ko](https://github.com/hyunwoongko), [Kichang Yang](https://github.com/jason9693), [Minho Ryu](https://github.com/bzantium), [Taekyoon Choi](https://github.com/Taekyoon), [Seungmu Yang](https://github.com/Ronalmoo), [jiwung Hyun](https://github.com/kabbi159), [Sungho Park](https://github.com/naem1023) 23 | 24 | 💡 We are collaborating with KoAlpaca team which is creating a series of Korean instruct fine-tuned models. As a result, we were able to release the Koalapca-Polyglot models. Please refer to [here](https://github.com/Beomi/KoAlpaca) to see more details. 25 | 26 | ### 2) Japanese StableLM 27 | We co-worked with StabilityAI Japan to create open source Japanese language models. We've mainly contributed to dataset collection part for this project. 28 | 29 | | Size | Training Status | Model Card | Model Checkpoints | 30 | |:-----------:|:------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------:|:-------------------------------------------------------------------------:| 31 | | 7B-base | Finished | [Available](https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b) | [Available](https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b/tree/main) | 32 | | 7B-instruct | Finished | [Available](https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b)| [Available](https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b/tree/main) | 33 | 34 | - Blog post: https://stability.ai/blog/stability-ai-new-jplm-japanese-language-model-stablelm 35 | - Contributors: [Hyunwoong Ko](https://github.com/hyunwoongko), [Fujiki Nakamura](https://github.com/fujiki-1emon), [Yunho Mo](https://github.com/momozzing), [Minji Jung](https://github.com/work82mj), [Sukyung Jang](https://github.com/skjang54), [KeunSeok Im](https://github.com/Mineru98) 36 | 37 | ## 3. Limitations and Biases 38 | Polyglot has been trained to optimize next token prediction. Language models such as this are often used for a wide variety of tasks and it is important to be aware of possible unexpected outcomes. For instance, Polyglot will not always return the most factual or accurate response but the most statistically likely one. In addition, Polyglot may produce socially unacceptable or offensive content. We recommend having a human curator or other filtering mechanism to censor sensitive content. 39 | 40 | ## 4. Citation and Related Information 41 | 42 | ### BibTeX entry 43 | If you find our work useful, please consider citing: 44 | ```bibtex 45 | @misc{ko2023technical, 46 | title={A Technical Report for Polyglot-Ko: Open-Source Large-Scale Korean Language Models}, 47 | author={Hyunwoong Ko and Kichang Yang and Minho Ryu and Taekyoon Choi and Seungmu Yang and jiwung Hyun and Sungho Park}, 48 | year={2023}, 49 | eprint={2306.02254}, 50 | archivePrefix={arXiv}, 51 | primaryClass={cs.CL} 52 | } 53 | ``` 54 | 55 | ```bibtex 56 | @misc{JapaneseStableLMBaseAlpha7B, 57 | url={[https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b](https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b)}, 58 | title={Japanese StableLM Base Alpha 7B}, 59 | author={Lee, Meng and Nakamura, Fujiki and Shing, Makoto and McCann, Paul and Akiba, Takuya and Orii, Naoki} 60 | } 61 | ``` 62 | 63 | ```bibtex 64 | @misc{JapaneseStableLMInstructAlpha7B, 65 | url={[https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b](https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b)}, 66 | title={Japanese StableLM Instruct Alpha 7B}, 67 | author={Lee, Meng and Nakamura, Fujiki and Shing, Makoto and McCann, Paul and Akiba, Takuya and Orii, Naoki} 68 | } 69 | ``` 70 | 71 | ### Licensing 72 | All our models are licensed under the terms of the Apache License 2.0. 73 | 74 | ``` 75 | Licensed under the Apache License, Version 2.0 (the "License"); 76 | you may not use this file except in compliance with the License. 77 | You may obtain a copy of the License at 78 | 79 | http://www.apache.org/licenses/LICENSE-2.0 80 | 81 | Unless required by applicable law or agreed to in writing, software 82 | distributed under the License is distributed on an "AS IS" BASIS, 83 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 84 | See the License for the specific language governing permissions and 85 | limitations under the License. 86 | ``` 87 | 88 | However, the model has the potential to generate unpredictable text as mentioned. Therefore, we are not responsible for any damages resulting from the use of the model. 89 | 90 | ### Acknowledgement 91 | This project was made possible thanks to the computing resources from [Stability.ai](https://stability.ai), thanks to [TUNiB](https://tunib.ai) for providing a large-scale Korean dataset. 92 | --------------------------------------------------------------------------------