commit 224f68937d3aca860d5fe868bf28d9f05e5d1890 Author: ModelHub XC Date: Fri Jun 19 09:44:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: shisa-ai/shisa-v2.1-lfm2-1.2b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b12e61e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +training_args.bin filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..25e731c --- /dev/null +++ b/LICENSE @@ -0,0 +1,71 @@ +LFM Open License v1.0 + +TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + +1. Definitions. + +"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by this document. + +"Licensor" shall mean Liquid AI, Inc. + +"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. + +"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. + +"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. + +"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. + +"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work. + +"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. + +"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." + +"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. + +"Commercial Use" shall mean any use of the Work for direct or indirect commercial advantage or monetary compensation. + +"Qualified Non-Profit Organization" shall mean a Legal Entity that is organized and operated exclusively for religious, charitable, scientific, testing for public safety, literary, or educational purposes, and which is exempt from federal income tax under Section 501(c)(3) of the United States Internal Revenue Code of 1986, as amended, or any equivalent non-profit or charitable organization in a foreign jurisdiction. + +"Non-Commercial or Research Purposes" shall mean purposes that do not involve any use of the Work or a Derivative Work for Commercial Use. + +"Threshold" shall mean annual revenue of 10 million United States dollars ($10,000,000) or more. + +2. Grant of Copyright License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. + +3. Grant of Patent License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. + +4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: + +(a) You must give any other recipients of the Work or Derivative Works a copy of this License; and + +(b) You must cause any modified files to carry prominent notices stating that You changed the files; and + +(c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and + +(d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. + +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 Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. + +5. Commercial Use Limitation. + +(a) The rights granted under this License for Commercial Use are conditioned upon You or Your Legal Entity not exceeding the Threshold. + +(b) Any Commercial Use of the Work or a Derivative Work by a Legal Entity that exceeds the Threshold is not licensed under this Agreement. + +(c) The Threshold shall not apply to a Qualified Non-Profit Organization's use of the Work or a Derivative Work for Non-Commercial or Research Purposes. + +6. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. + +7. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except for the reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. + +8. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) 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 Work and assume any risks associated with Your exercise of permissions under this License. + +9. Limitation of Liability. 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, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (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 such Contributor has been advised of the possibility of such damages. + +10. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. + +11. Termination. This License will terminate automatically and immediately if You fail to comply with any of its terms and conditions. Upon termination, You must cease all use of the Work and any Derivative Works and delete all copies in Your possession. + +END OF TERMS AND CONDITIONS \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6660e2 --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +model_name: Shisa V2.1 1.2B +license: other +license_name: lfm1.0 +license_link: LICENSE +pipeline_tag: text-generation +language: +- ja +- en +tags: +- shisa +- lfm2 +- axolotl +- trl +base_model: +- LiquidAI/LFM2-1.2B +datasets: +- shisa-ai/shisa-v2.1-sharegpt +--- +# Shisa V2.1 + +**Shisa V2.1** is an update to our [Shisa V2](https://huggingface.co/collections/shisa-ai/shisa-v2) family of bilingual Japanese and English (JA/EN) general-purpose chat models trained by [Shisa.AI](https://shisa.ai/). These models aim to excel in Japanese language tasks while retaining robust English capabilities. + +Following the release of our [Shisa V2 405B](https://huggingface.co/shisa-ai/shisa-v2-llama3.1-405b) model, we resampled a [new version of our Shisa V2 dataset](https://huggingface.co/datasets/shisa-ai/shisa-v2.1-sharegpt) and found a noticeable performance uplift. V2.1 started as a "quick" update with this and some other data fixes, but led to updates and improvements to almost all of our Shisa V2 datasets, as well as several new additions for better instruction following, translation, politeness, and other Japanese-specific language improvements. Beyond re-tuned SFT and DPO recipes, some of these new models integrate additional model-merging and RL stages as well. + +The initial Shisa V2.1 release includes improved versions of our most popular 14B and 70B class models as well as new models at 1.2B, 3B, and 8B sizes suitable for local and edge-based use cases. Each has class-leading Japanese-language performance at their respective size. + +| License | Model | Parameters | Context Length | JA AVG | EN AVG | +| :---- | :---- | ----: | ----: | ----: | ----: | +| LFM | [shisa-v2.1-lfm2-1.2b](https://huggingface.co/shisa-ai/shisa-v2.1-lfm2-1.2b) | 1.2B | 32K | 43.4 | 27.6 | +| Llama 3.2 | [shisa-v2.1-llama3.2-3b](https://huggingface.co/shisa-ai/shisa-v2.1-llama3.2-3b) | 3B | 128K | 57.9 | 43.2 | +| Apache 2.0 | [shisa-v2.1-qwen3-8b](https://huggingface.co/shisa-ai/shisa-v2.1-qwen3-8b) | 8B | 32K/128K | 67.8 | 57.8 | +| MIT | [shisa-v2.1-unphi4-14b](https://huggingface.co/shisa-ai/shisa-v2.1-unphi4-14b) | 14B | 16K | 72.6 | 57.7 | +| Llama 3.3 | [shisa-v2.1-llama3.3-70b](https://huggingface.co/shisa-ai/shisa-v2.1-llama3.3-70b) | 70B | 128K | 73.1 | 66.0 | + + +## Performance + +Shisa V2.1 model development was guided by the latest version (V2.1) of our internal `multieval` test battery and is not directly comparable to our previous Shisa V2 testing so for convenience, we have included a table showing direct comparisons to our prior models: + +| Model | JA AVG | EN AVG | Shaberi V2.1 | +| ----- | -----: | -----: | -----: | +| shisa-v2-llama3.1-405b | 74.7 | 67.5 | 8.31 | +| **shisa-v2.1-llama3.3-70b** | 73.1 | 66.0 | 8.03 | +| **shisa-v2.1-unphi4-14b** | 72.6 | 57.7 | 7.71 | +| shisa-v2-llama3.3-70b | 69.0 | 64.3 | 7.68 | +| shisa-v2-unphi4-14b | 68.7 | 66.7 | 7.62 | +| **shisa-v2.1-qwen3-8b** | 67.8 | 57.8 | 7.35 | +| shisa-v2-llama3.1-8b | 58.7 | 55.1 | 6.43 | +| **shisa-v2.1-llama3.2-3b** | 57.9 | 43.2 | 6.23 | +| **shisa-v2.1-lfm2-1.2b** | 43.4 | 27.6 | 5.35 | + +Shisa V2.1 14B exceeds Shisa V2 70B in Japanese language benchmark performance, and our Shisa V2.1 70B is approaching Shisa V2 405B performance. These gains were achieved without any benchmark-specific targeted training, and based on both the broad coverage of our evals as well as our own production deployments of variants of these models, we believe they reflect actual improvements in real-world Japanese-language capabilities. + +Besides changes to our MultiEval composition, our Shaberi scores are not comparable to earlier scores as we have made some modifications to the prompts and also now use GPT-5.1 (`gpt-5.1-2025-11-13`) as our Shaberi LLM Judge. GPT-5.1 scores answers significantly lower than the GPT-4.1 (`gpt-4.1-2025-04-14`) judge we used for V2. + +### Japanese MT-Bench + +As pointed out in our [Shisa V2 405B Overview Report](https://shisa.ai/posts/shisa-v2-405b/#overview-report), as our models have approached and surpassed the commonly used LLM Judge (GPT-4) in Japanese language capabilities, those judgments have become less useful for model development. For Shisa V2, we switched our Japanese MT-Bench testing to using GPT-4.1 for stricter and more discriminating scores, and for Shisa V2.1 we switched again to GPT-5.1, which we found to be even better at helping us judge model quality. + +However, for easier reference and comparison to other models, we’ve included a table of our JA MT-Bench results using a [dedicated "canonical version" test harness](https://github.com/shisa-ai/ja-mt-bench-harness) that should be more directly comparable with the scores posted by other models online. Our repo also contains the raw answers and judgments for our tested models for replication or future re-judging. (It also includes a number of custom statistical analysis scripts which may be of interest.) + +| Model | GPT-4-Turbo | GPT-4o | GPT-4.1 | GPT-5.1 | +| :---- | ----: | ----: | ----: | ----: | +| shisa-ai/shisa-v2-llama3.1-405b | 9.43 | 8.92 | 9.13 | 7.66 | +| **shisa-ai/shisa-v2.1-llama3.3-70b** | 9.26 | 8.74 | 8.69 | 7.24 | +| **shisa-ai/shisa-v2.1-unphi4-14b** | 9.28 | 8.50 | 8.68 | 7.07 | +| shisa-ai/shisa-v2-llama3.3-70b | 9.07 | 8.44 | 8.41 | 6.82 | +| shisa-ai/shisa-v2-unphi4-14b | *8.69* | 8.38 | 8.30 | 6.51 | +| **shisa-ai/shisa-v2.1-qwen3-8b** | *8.93* | 8.10 | 8.04 | 6.39 | +| shisa-ai/shisa-v2-qwen2.5-7b | 8.16 | 7.62 | 7.31 | 5.79 | +| shisa-ai/shisa-v2-llama3.1-8b | 7.97 | 7.41 | 6.99 | 5.44 | +| **shisa-ai/shisa-v2.1-llama3.2-3b** | 7.55 | 6.94 | 6.42 | 4.92 | +| **shisa-ai/shisa-v2.1-lfm2-1.2b** | 6.69 | 6.13 | 5.55 | 4.19 | + + +### Cross-Lingual Token Leakage + +While reviewing eval results, we noticed that many models can score highly on Japanese language benchmarks but still output non-Japanese words or sub-words (tokens). Internally we refer to this as Cross-Lingual Token Leakage (CLTL). It has also been referred to more generally as "word-level language confusion" (Marchisio et al., "[Understanding and Mitigating Language Confusion in LLMs](https://arxiv.org/abs/2406.20052)," Cohere). + +We see many strong multilingual models that exhibit language confusion behavior, but quantifying (and reliably identifying) this issue is harder than one might expect because not only do Japanese and Chinese share Unicode code-planes, but also many valid English words can commonly appear in Japanese text. (Think "AI", "VR", or common words and acronyms like "Google" or "NATO"). This is compounded by the fact that even frontier models suffer from “token blindness” - they are often unable to disentangle the meaning from the actual language of the tokens and often fail to recognize wrong-language tokens. + +For Shisa V2.1, we have developed a brand-new class of Japanese evaluation benchmark specifically designed to identify CLTL, which can both measure and specifically identify wrong language tokens. + +| Base Model | Shisa V2.1 Model | Base Leak % | Shisa V2.1 Leak % | Leakage Improvement | +| ----- | ----- | -----: | -----: | -----: | +| Llama-3.2-3B-Instruct | shisa-v2.1-llama3.2-3b | 11.48% | 0.24% | 47.8× | +| LFM2-1.2B | shisa-v2.1-lfm2-1.2b | 4.32% | 0.32% | 13.5× | +| Qwen3-8B | shisa-v2.1-qwen3-8b | 2.18% | 0.44% | 5.0× | +| Llama-3.3-70B-Instruct | shisa-v2.1-llama3.3-70b | 1.90% | 0.36% | 5.3× | +| phi-4 | shisa-v2.1-unphi4-14b | 0.12% | 0.06% | 2.0× | + +We believe eliminating both CLTL and language confusion in general is of the utmost importance for deploying LLMs for most Japanese-language production use cases (e.g., translation, customer service, or even basic writing tasks) and we plan to continue to both improve our detection heuristics and to integrate it into all our future evaluation grading, as well as use our better CLTL detection to further improve our training methods. We will be publishing more details in-depth in a future writeup. + +### MultiEval 2.1 + +Our primary MultiEval V2.1 suite is a mixed battery of 10 Japanese and 7 English/general evaluations designed to give a broad picture of overall model performance across a variety of common general language tasks. + +#### Japanese +- **[Shaberi v2.1](https://github.com/shisa-ai/shaberi)** - Our public fork of [LightBlue’s Shaberi](https://github.com/lightblue-tech/japanese_llm_eval) suite, extended for reasoning models, updated judges, output viewing, and errata fixes; despite some known issues, it remains our primary functional benchmark for quickly evaluating general Japanese LLM performance. All Shaberi scores in V2.1 are judged by GPT‑5.1 (`gpt-5.1-2025-11-13`). + - **[ELYZA Tasks 100](https://huggingface.co/datasets/elyza/ELYZA-tasks-100)** - A set of 100 complex Japanese instructions and tasks graded on a 5‑point rubric, targeting realistic instruction-following and generation quality. + - **[Japanese MT-Bench](https://github.com/Stability-AI/FastChat)** - A high quality Japanese adaptation of MT-Bench with eight categories of conversational and writing outputs, evaluated by an LLM judge on a 1–10 scale to capture stylistic and qualitative differences. + - **[Rakuda](https://huggingface.co/datasets/yuzuai/rakuda-questions)** - An adaptation of [Rakuda](https://yuzuai.jp/benchmark), a Japanese-language trivia QA benchmark covering Japanese-focused factual knowledge and recall; scored via exact-match style metrics. + - **[Tengu](https://huggingface.co/datasets/lightblue/tengu_bench)** - A heterogeneous grab-bag of Japanese tasks (reasoning, QA, and writing) that is a useful secondary stress test for general capability. +- **[M‑IFEval](https://github.com/shisa-ai/M-IFEval) (JA slice)** - Our public fork of [LightBlue’s multilingual IFEval](https://github.com/lightblue-tech/M-IFEval) which fixes a number of errata; in the main Japanese composite we currently use only the Japanese subset, exposing it as **M‑IFja**, with rule-based instruction‑compliance scoring. We report the `loose` score. +- **[shisa-jp-ifeval](https://github.com/shisa-ai/shisa-jp-ifeval)** - Shisa.AI's own Japanese-specific IFEval variant, carefully replacing English‑centric constraints (spelling, capitalization, etc.) with verifiable Japanese constraints (mora counting, script choice, honorifics, etc.) and rule-based scoring. +- **[shisa-jp-rp-bench](https://github.com/shisa-ai/shisa-jp-rp-bench)** - A Japanese roleplay/persona benchmark based on [Aratako’s Japanese-RP-Bench](https://github.com/Aratako/Japanese-RP-Bench), using multi-turn conversations and pairwise LLM judging (Gemini 2.0 Flash) with a Bradley-Terry model to produce stable RP rankings. +- **[shisa-jp-tl-bench](https://github.com/shisa-ai/shisa-jp-tl-bench)** – English↔Japanese translation shootout: the target model’s translations are compared pairwise against a frozen base set and judged by a dedicated LLM judge (Gemini 2.5 Flash), then aggregated with a Bradley-Terry logistic model into a 0–10‑style score. +- **kiseki-eval** - A private Shisa.AI translation eval focused on subtle aspects of Japanese such as tone, gendering, and terms of endearment; translations are judged by Gemini 2.5 Pro using an Ultrafeedback‑style 1–5 rubric. +- **chotto-eval** - Another [Shisa.AI](http://shisa.ai/) internal eval, cross‑lingual multi‑turn interaction set mimicking real conversational flows; we do pairwise LLM‑vs‑LLM comparison against a fixed [chotto.chat](https://chotto.chat/) strong internal baseline model (which has a roughly 50% win/loss against Claude Opus 4.1 and Gemini 2.5 Flash) using Gemini 2.5 Pro as evaluator. + +#### English/General +- **[MixEval Easy](https://huggingface.co/datasets/MixEval/MixEval)** - A fast, mixed English reasoning benchmark (`mixeval_easy` task in Lighteval/Inspect) combining free‑form and multiple‑choice questions with 0.96 correlation with 2024 Chatbot Arena rankings; scored both by the task’s exact metrics and by LLM judges (Flow‑Judge `flowaicom/Flow-Judge-v0.1` and a GPT judge, default `gpt-4.1-mini-2025-04-14`) via the HF [Lighteval](https://github.com/huggingface/lighteval) runner. +- **[MixEval Hard](https://huggingface.co/datasets/MixEval/MixEval)** - A harder subset of MixEval (`mixeval_hard`) designed to better separate strong models, run through the same Lighteval/Inspect pipeline and Flow‑Judge + GPT‑judge scoring as MixEval Easy. +- **[LiveBench](https://github.com/shisa-ai/LiveBench)** - Our public fork of [LiveBench](https://github.com/LiveBench/LiveBench/tree/main), a contamination‑aware, continually updated English benchmark covering coding, math, reasoning, language, data analysis, and instruction following, judged with LiveBench's own rule-based and ground-truth scoring (no LLM judge). We use the latest public dataset `LiveBench-2024-11-25`. Our fork supports concurrent runs, GPT-5.1 reasoning semantics, and other fixes. +- **[GPQA Diamond](https://github.com/idavidrein/gpqa)** - PhD‑level multiple‑choice science QA from the Diamond split of GPQA (Lighteval `gpqa:diamond` task using [Idavidrein/gpqa](https://huggingface.co/datasets/Idavidrein/gpqa)); we score with Inspect’s multiple‑choice `choice` metric and an additional robustness pass that recovers bare letter answers, so this remains a pure reference‑based metric (no LLM judge). +- **[Google IFEval](https://github.com/google-research/google-research/tree/master/instruction_following_eval) (EN)** – An English-language instruction‑following benchmark from Google Research (`ifeval` task in Lighteval/Inspect over [google/IFEval](https://huggingface.co/datasets/google/IFEval)), scored with the original rule-based `check_following` functions; we report the `loose` prompt‑level accuracy, with no LLM judge involved. +- **[IFBench](https://github.com/shisa-ai/IFBench)** – Our public fork of [AI2's IFBench](https://github.com/allenai/IFBench) IFEval-inspired (but less saturated) instruction‑following suite, `loose` prompt-level accuracies using IFBench's own verification functions (no LLM judge). We fix some evaluation bugs and add a response generation script for parallel execution against OpenAI-compatible endpoints. +- **[HumanEval+](https://github.com/shisa-ai/evalplus)** – Using our public fork of [EvalPlus](https://github.com/evalplus/evalplus), which adds direct OpenAI/Gemini support as well as parallel generation support, we run HumanEval+ and report the `plus-pass@1` score (reference/test-based judgment). + +| Eval | V2.1 1.2B | V2.1 3B | V2.1 8B | V2.1 14B | V2.1 70B | +| ----- | ----- | ----- | ----- | ----- | ----- | +| **JA AVG** | 43.4 | 57.9 | 67.8 | 72.6 | 73.1 | +| **EN AVG** | 27.6 | 43.2 | 57.8 | 57.7 | 66.0 | +| **Shaberi v2.1** | 5.347 | 6.231 | 7.353 | 7.713 | 8.029 | +| **ELYZA 100** | 5.480 | 6.700 | 7.660 | 8.270 | 8.360 | +| **JA MT-Bench** | 5.496 | 6.026 | 7.783 | 7.867 | 7.967 | +| **Rakuda** | 5.500 | 6.425 | 7.150 | 7.562 | 8.275 | +| **Tengu** | 4.913 | 5.774 | 6.817 | 7.152 | 7.513 | +| **M-IFEval (JA)** | 0.355 | 0.424 | 0.471 | 0.529 | 0.587 | +| **shisa-jp-ifeval** | 0.167 | 0.260 | 0.347 | 0.407 | 0.453 | +| **shisa-jp-rp-bench** | 2.521 | 4.714 | 4.792 | 4.745 | 4.656 | +| **shisa-jp-tl-bench** | 3.425 | 7.886 | 8.917 | 9.494 | 9.551 | +| **kiseki-eval** | 3.182 | 3.318 | 3.580 | 3.977 | 3.970 | +| **chotto-eval** | 0.200 | 0.218 | 0.455 | 0.545 | 0.382 | +| **MixEval Easy** | 0.422 | 0.719 | 0.802 | 0.848 | 0.915 | +| **MixEval Hard** | 0.266 | 0.493 | 0.607 | 0.655 | 0.789 | +| **LiveBench** | 13.2 | 21.7 | 45.7 | 38.8 | 50.0 | +| **GPQA Diamond** | 0.141 | 0.303 | 0.328 | 0.429 | 0.419 | +| **IFEval** | 0.512 | 0.584 | 0.791 | 0.623 | 0.880 | +| **IFBench** | 0.173 | 0.214 | 0.259 | 0.265 | 0.340 | +| **HumanEval+** | 0.287 | 0.494 | 0.805 | 0.829 | 0.780 | + +## Credits + +The Shisa V2.1 models were developed by [Leonard Lin](https://huggingface.co/leonardlin) and [Adam Lensenmayer](https://huggingface.co/NekoMikoReimu) of [Shisa.AI](https://huggingface.co/shisa-ai). + +Our models would not exist without the contributions of the open source and open models community and our generous compute sponsors. + +Primary compute for Shisa V2.1 model training was provided by AMD and all our final Shisa V2.1 models (and several hundred ablations) were trained on an AMD MI300X node provided by the [AMD Developer Cloud](https://www.amd.com/en/developer/resources/cloud-access/amd-developer-cloud.html) using [Axolotl](https://github.com/axolotl-ai-cloud/axolotl). RL was done directly with Hugging Face [TRL](https://github.com/huggingface/trl) and merging with Arcee AI's [mergekit](https://github.com/arcee-ai/mergekit). + +Additional compute and credits used for ablations, data processing, and evaluations were provided by: [Chutes](https://chutes.ai/), [Hot Aisle](https://hotaisle.xyz/), [Emerald Compute System](https://ecp.cc/), [Lambda](https://lambda.ai/), and [Strata](https://strata.co.jp/). + +We are also thankful for the active support from the [AWS Activate](https://aws.amazon.com/activate/activate-landing/), [Google for Startups](https://startup.google.com/), and [NVIDIA Inception](https://www.nvidia.com/en-us/startups/) programs. + + +# Additional Models + +While not part of our official Shisa V2.1 release, over the course of training we have created a few other interesting models along the way. + +- [037-rakuten-2.0-mini-instruct-1.5b-v2new-dpo405b](https://huggingface.co/shisa-ai/037-rakuten-2.0-mini-instruct-1.5b-v2new-dpo405b) - trained to commemorate a Rakuten AI office visit/onsite talk, this was our first experiment trying our new Shisa V2.x dataset on a smaller model (1.5B) - its performance is superseded by our [Shisa V2.1 1.2B](https://huggingface.co/shisa-ai/shisa-v2.1-lfm2-1.2b/) model, but it further enhanced our confidence that our training could improve even very strong Japanese SLMs. +- [shisa-v2.1c-lfm2-350m](https://huggingface.co/shisa-ai/shisa-v2.1c-lfm2-350m) - this small model was trained for the LiquidAI Tokyo Hackathon and again surprised us. It is SOTA for Japanese at <1B (and appears to largely fix the base model's CLTL issues). There is also a dedicated [JA-EN translation tune](https://huggingface.co/shisa-ai/shisa-v2.1c-lfm2-350m-sft3-tlonly) that is surprisingly capable. +- [031-swallow-8b-0.5-base-v2new-dpo405b](https://huggingface.co/shisa-ai/031-swallow-8b-0.5-base-v2new-dpo405b) - trained on the latest [Swallow 0.5 CPT base model](https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.5), this was SOTA when published, but is superseded by our [Shisa V2.1 8B](https://huggingface.co/shisa-ai/shisa-v2.1-qwen3-8b) model. Due to the Gemma + Llama dual licensing, we do not believe this model is actually suitable for commercial or research use, but we were curious to see the results of our new training on a strong Japanese non-instruction-tuned base model. +- [shisa-v1-7b-v2.1](https://huggingface.co/shisa-ai/shisa-v1-7b-v2.1) - our original [Shisa 7B V1](https://huggingface.co/augmxnt/shisa-7b-v1) model was trained 2 years ago, and we celebrated the anniversary by experimenting with additional re-training of the original model to see how much it could be improved- a fair bit actually, but its performance is still much lower than modern models. We recommend using our [Shisa V2.1 8B](https://huggingface.co/shisa-ai/shisa-v2.1-qwen3-8b) model instead. + +During the course of Shisa V2.1 development we have ported the [HF megablocks](https://huggingface.co/kernels-community/megablocks) kernel to [shisa-ai/megablocks-hip](https://huggingface.co/shisa-ai/megablocks-hip), with numerically validated, 4-5X performance gains for HF/TRL based trainers on AMD MI300X GPUs. We have also ported Aux Loss Free Balancing as an Axolotl plugin for multiple MoE architectures and a distributed-compatible (FSDP2 & DSZ3) Muon-clip optimizer. + +For more details on our development and insights, please visit the [Shisa V2 Github repository](https://github.com/shisa-ai/shisa-v2) and the [Shisa.AI website](https://shisa.ai/). + +--- + +*Per the Llama Community License Agreements, the official names of the Llama-based models are "Llama 3.2 Shisa V2.1 3B" and "Llama 3.3 Shisa V2.1 70B"* \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..ed66b6d --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,37 @@ +{{- bos_token -}} +{%- set system_prompt = "" -%} +{%- set ns = namespace(system_prompt="") -%} +{%- if messages[0]["role"] == "system" -%} + {%- set ns.system_prompt = messages[0]["content"] -%} + {%- set messages = messages[1:] -%} +{%- endif -%} +{%- if tools -%} + {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} + {%- for tool in tools -%} + {%- if tool is not string -%} + {%- set tool = tool | tojson -%} + {%- endif -%} + {%- set ns.system_prompt = ns.system_prompt + tool -%} + {%- if not loop.last -%} + {%- set ns.system_prompt = ns.system_prompt + ", " -%} + {%- endif -%} + {%- endfor -%} + {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%} +{%- endif -%} +{%- if ns.system_prompt -%} + {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}} +{%- endif -%} +{%- for message in messages -%} + {{- "<|im_start|>" + message["role"] + "\n" -}} + {%- set content = message["content"] -%} + {%- if content is not string -%} + {%- set content = content | tojson -%} + {%- endif -%} + {%- if message["role"] == "tool" -%} + {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%} + {%- endif -%} + {{- content + "<|im_end|>\n" -}} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{- "<|im_start|>assistant\n" -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..47631cb --- /dev/null +++ b/config.json @@ -0,0 +1,57 @@ +{ + "architectures": [ + "Lfm2ForCausalLM" + ], + "block_auto_adjust_ff_dim": true, + "block_dim": 2048, + "block_ff_dim": 12288, + "block_ffn_dim_multiplier": 1.0, + "block_mlp_init_scale": 1.0, + "block_multiple_of": 256, + "block_norm_eps": 1e-05, + "block_out_init_scale": 1.0, + "block_use_swiglu": true, + "block_use_xavier_init": true, + "bos_token_id": 1, + "conv_L_cache": 3, + "conv_bias": false, + "conv_dim": 2048, + "conv_dim_out": 2048, + "conv_use_xavier_init": true, + "dtype": "bfloat16", + "eos_token_id": 7, + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "conv", + "conv", + "full_attention", + "conv", + "conv", + "full_attention", + "conv", + "conv", + "full_attention", + "conv", + "full_attention", + "conv", + "full_attention", + "conv", + "full_attention", + "conv" + ], + "max_position_embeddings": 128000, + "model_type": "lfm2", + "norm_eps": 1e-05, + "num_attention_heads": 32, + "num_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pad_token_id": 0, + "rope_theta": 1000000.0, + "transformers_version": "4.57.1", + "use_cache": false, + "use_pos_enc": true, + "vocab_size": 65536 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/debug.log b/debug.log new file mode 100644 index 0000000..740cf4e --- /dev/null +++ b/debug.log @@ -0,0 +1,9 @@ +[2025-11-06 08:51:25,486] [WARNING] [py.warnings._showwarnmsg:112] [PID:3076758] /root/miniforge3/envs/axolotl/lib/python3.12/site-packages/deepspeed/runtime/zero/partition_parameters.py:240: UserWarning: expandable_segments not supported on this platform (Triggered internally at /pytorch/c10/hip/HIPAllocatorConfig.h:36.) + tensor: Tensor = fn(*args, **kwargs) + +[2025-11-06 08:51:32,980] [WARNING] [py.warnings._showwarnmsg:112] [PID:3076758] /root/miniforge3/envs/axolotl/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4807: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. + warnings.warn( # warn only once + + Extracting prompt in train dataset (num_proc=160): 0%| | 0/105170 [00:00", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5900663 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cff83b4f6d7e9d8929bebc62b07e92cf1b3f99c80d16bafe8b84a75448f40b +size 4732426 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7b3257a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,4078 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "<|pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "<|fim_pre|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "<|fim_mid|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "<|fim_suf|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "8": { + "content": "<|tool_list_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "9": { + "content": "<|tool_list_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "10": { + "content": "<|tool_call_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "11": { + "content": "<|tool_call_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "12": { + "content": "<|tool_response_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "13": { + "content": "<|tool_response_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "16": { + "content": "<|reserved_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "17": { + "content": "<|reserved_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "18": { + "content": "<|reserved_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "19": { + "content": "<|reserved_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "20": { + "content": "<|reserved_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "21": { + "content": "<|reserved_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "22": { + "content": "<|reserved_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "23": { + "content": "<|reserved_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "24": { + "content": "<|reserved_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "25": { + "content": "<|reserved_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "26": { + "content": "<|reserved_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "27": { + "content": "<|reserved_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "28": { + "content": "<|reserved_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "29": { + "content": "<|reserved_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "30": { + "content": "<|reserved_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "31": { + "content": "<|reserved_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32": { + "content": "<|reserved_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "33": { + "content": "<|reserved_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "34": { + "content": "<|reserved_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "35": { + "content": "<|reserved_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "36": { + "content": "<|reserved_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "37": { + "content": "<|reserved_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "38": { + "content": "<|reserved_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "39": { + "content": "<|reserved_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "40": { + "content": "<|reserved_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "41": { + "content": "<|reserved_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "42": { + "content": "<|reserved_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "43": { + "content": "<|reserved_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "44": { + "content": "<|reserved_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "45": { + "content": "<|reserved_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "46": { + "content": "<|reserved_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "47": { + "content": "<|reserved_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "48": { + "content": "<|reserved_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "49": { + "content": "<|reserved_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "50": { + "content": "<|reserved_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "51": { + "content": "<|reserved_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "52": { + "content": "<|reserved_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "53": { + "content": "<|reserved_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "54": { + "content": "<|reserved_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "55": { + "content": "<|reserved_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "56": { + "content": "<|reserved_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "57": { + "content": "<|reserved_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "58": { + "content": "<|reserved_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "59": { + "content": "<|reserved_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "60": { + "content": "<|reserved_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61": { + "content": "<|reserved_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "62": { + "content": "<|reserved_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "63": { + "content": "<|reserved_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64": { + "content": "<|reserved_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "65": { + "content": "<|reserved_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "66": { + "content": "<|reserved_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "67": { + "content": "<|reserved_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "68": { + "content": "<|reserved_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "69": { + "content": "<|reserved_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "70": { + "content": "<|reserved_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71": { + "content": "<|reserved_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "72": { + "content": "<|reserved_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "73": { + "content": "<|reserved_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "74": { + "content": "<|reserved_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "75": { + "content": "<|reserved_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "76": { + "content": "<|reserved_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "77": { + "content": "<|reserved_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "78": { + "content": "<|reserved_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "79": { + "content": "<|reserved_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "80": { + "content": "<|reserved_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "81": { + "content": "<|reserved_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "82": { + "content": "<|reserved_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "83": { + "content": "<|reserved_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "84": { + "content": "<|reserved_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "85": { + "content": "<|reserved_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "86": { + "content": "<|reserved_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "87": { + "content": "<|reserved_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "88": { + "content": "<|reserved_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "89": { + "content": "<|reserved_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "90": { + "content": "<|reserved_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "91": { + "content": "<|reserved_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "92": { + "content": "<|reserved_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "93": { + "content": "<|reserved_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "94": { + "content": "<|reserved_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "95": { + "content": "<|reserved_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "96": { + "content": "<|reserved_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "97": { + "content": "<|reserved_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "98": { + "content": "<|reserved_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "99": { + "content": "<|reserved_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100": { + "content": "<|reserved_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "101": { + "content": "<|reserved_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "102": { + "content": "<|reserved_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "103": { + "content": "<|reserved_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "104": { + "content": "<|reserved_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "105": { + "content": "<|reserved_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "106": { + "content": "<|reserved_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "<|reserved_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "<|reserved_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "109": { + "content": "<|reserved_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "110": { + "content": "<|reserved_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "111": { + "content": "<|reserved_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "112": { + "content": "<|reserved_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "113": { + "content": "<|reserved_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "114": { + "content": "<|reserved_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "115": { + "content": "<|reserved_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "116": { + "content": "<|reserved_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "117": { + "content": "<|reserved_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "118": { + "content": "<|reserved_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "119": { + "content": "<|reserved_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "120": { + "content": "<|reserved_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "121": { + "content": "<|reserved_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "122": { + "content": "<|reserved_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "123": { + "content": "<|reserved_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "124": { + "content": "<|reserved_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "125": { + "content": "<|reserved_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "126": { + "content": "<|reserved_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "127": { + "content": "<|reserved_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128": { + "content": "<|reserved_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "129": { + "content": "<|reserved_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "130": { + "content": "<|reserved_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "131": { + "content": "<|reserved_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "132": { + "content": "<|reserved_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "133": { + "content": "<|reserved_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "134": { + "content": "<|reserved_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "135": { + "content": "<|reserved_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "136": { + "content": "<|reserved_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "137": { + "content": "<|reserved_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "138": { + "content": "<|reserved_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "139": { + "content": "<|reserved_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "140": { + "content": "<|reserved_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "141": { + "content": "<|reserved_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "142": { + "content": "<|reserved_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "143": { + "content": "<|reserved_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "144": { + "content": "<|reserved_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "145": { + "content": "<|reserved_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "146": { + "content": "<|reserved_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "147": { + "content": "<|reserved_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "148": { + "content": "<|reserved_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "149": { + "content": "<|reserved_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "150": { + "content": "<|reserved_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151": { + "content": "<|reserved_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "152": { + "content": "<|reserved_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "153": { + "content": "<|reserved_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "154": { + "content": "<|reserved_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "155": { + "content": "<|reserved_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "156": { + "content": "<|reserved_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "157": { + "content": "<|reserved_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "158": { + "content": "<|reserved_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "159": { + "content": "<|reserved_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "160": { + "content": "<|reserved_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "161": { + "content": "<|reserved_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "162": { + "content": "<|reserved_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "163": { + "content": "<|reserved_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "164": { + "content": "<|reserved_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "165": { + "content": "<|reserved_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "166": { + "content": "<|reserved_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "167": { + "content": "<|reserved_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "168": { + "content": "<|reserved_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "169": { + "content": "<|reserved_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "170": { + "content": "<|reserved_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "171": { + "content": "<|reserved_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "172": { + "content": "<|reserved_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "173": { + "content": "<|reserved_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "174": { + "content": "<|reserved_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "175": { + "content": "<|reserved_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "176": { + "content": "<|reserved_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "177": { + "content": "<|reserved_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "178": { + "content": "<|reserved_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "179": { + "content": "<|reserved_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "180": { + "content": "<|reserved_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "181": { + "content": "<|reserved_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "182": { + "content": "<|reserved_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "183": { + "content": "<|reserved_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "184": { + "content": "<|reserved_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "185": { + "content": "<|reserved_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "186": { + "content": "<|reserved_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "187": { + "content": "<|reserved_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "188": { + "content": "<|reserved_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "189": { + "content": "<|reserved_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "190": { + "content": "<|reserved_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "191": { + "content": "<|reserved_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "192": { + "content": "<|reserved_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "193": { + "content": "<|reserved_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "194": { + "content": "<|reserved_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "195": { + "content": "<|reserved_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "196": { + "content": "<|reserved_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "197": { + "content": "<|reserved_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "198": { + "content": "<|reserved_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "199": { + "content": "<|reserved_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200": { + "content": "<|reserved_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "201": { + "content": "<|reserved_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "202": { + "content": "<|reserved_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "203": { + "content": "<|reserved_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "204": { + "content": "<|reserved_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "205": { + "content": "<|reserved_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "206": { + "content": "<|reserved_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "207": { + "content": "<|reserved_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "208": { + "content": "<|reserved_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "209": { + "content": "<|reserved_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "210": { + "content": "<|reserved_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "211": { + "content": "<|reserved_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "212": { + "content": "<|reserved_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "213": { + "content": "<|reserved_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "214": { + "content": "<|reserved_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "215": { + "content": "<|reserved_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "216": { + "content": "<|reserved_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "217": { + "content": "<|reserved_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "218": { + "content": "<|reserved_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "219": { + "content": "<|reserved_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "220": { + "content": "<|reserved_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "221": { + "content": "<|reserved_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "222": { + "content": "<|reserved_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "223": { + "content": "<|reserved_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "224": { + "content": "<|reserved_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "225": { + "content": "<|reserved_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "226": { + "content": "<|reserved_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "227": { + "content": "<|reserved_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "228": { + "content": "<|reserved_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "229": { + "content": "<|reserved_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "230": { + "content": "<|reserved_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "231": { + "content": "<|reserved_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "232": { + "content": "<|reserved_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "233": { + "content": "<|reserved_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "234": { + "content": "<|reserved_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "235": { + "content": "<|reserved_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "236": { + "content": "<|reserved_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "237": { + "content": "<|reserved_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "238": { + "content": "<|reserved_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "239": { + "content": "<|reserved_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "240": { + "content": "<|reserved_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "241": { + "content": "<|reserved_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "242": { + "content": "<|reserved_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "243": { + "content": "<|reserved_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "244": { + "content": "<|reserved_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "245": { + "content": "<|reserved_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "246": { + "content": "<|reserved_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "247": { + "content": "<|reserved_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "248": { + "content": "<|reserved_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "249": { + "content": "<|reserved_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "250": { + "content": "<|reserved_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "251": { + "content": "<|reserved_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "252": { + "content": "<|reserved_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "253": { + "content": "<|reserved_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "254": { + "content": "<|reserved_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255": { + "content": "<|reserved_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "256": { + "content": "<|reserved_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "257": { + "content": "<|reserved_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "258": { + "content": "<|reserved_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "259": { + "content": "<|reserved_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "260": { + "content": "<|reserved_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261": { + "content": "<|reserved_251|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "262": { + "content": "<|reserved_252|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "263": { + "content": "<|reserved_253|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "264": { + "content": "<|reserved_254|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "265": { + "content": "<|reserved_255|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "266": { + "content": "<|reserved_256|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "267": { + "content": "<|reserved_257|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "268": { + "content": "<|reserved_258|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "269": { + "content": "<|reserved_259|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "270": { + "content": "<|reserved_260|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "271": { + "content": "<|reserved_261|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "272": { + "content": "<|reserved_262|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "273": { + "content": "<|reserved_263|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "274": { + "content": "<|reserved_264|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "275": { + "content": "<|reserved_265|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "276": { + "content": "<|reserved_266|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "277": { + "content": "<|reserved_267|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "278": { + "content": "<|reserved_268|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "279": { + "content": "<|reserved_269|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "280": { + "content": "<|reserved_270|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "281": { + "content": "<|reserved_271|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "282": { + "content": "<|reserved_272|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "283": { + "content": "<|reserved_273|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "284": { + "content": "<|reserved_274|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "285": { + "content": "<|reserved_275|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "286": { + "content": "<|reserved_276|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "287": { + "content": "<|reserved_277|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "288": { + "content": "<|reserved_278|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "289": { + "content": "<|reserved_279|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "290": { + "content": "<|reserved_280|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "291": { + "content": "<|reserved_281|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "292": { + "content": "<|reserved_282|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "293": { + "content": "<|reserved_283|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "294": { + "content": "<|reserved_284|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "295": { + "content": "<|reserved_285|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "296": { + "content": "<|reserved_286|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "297": { + "content": "<|reserved_287|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "298": { + "content": "<|reserved_288|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "299": { + "content": "<|reserved_289|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "300": { + "content": "<|reserved_290|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "301": { + "content": "<|reserved_291|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "302": { + "content": "<|reserved_292|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "303": { + "content": "<|reserved_293|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "304": { + "content": "<|reserved_294|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "305": { + "content": "<|reserved_295|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "306": { + "content": "<|reserved_296|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "307": { + "content": "<|reserved_297|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "308": { + "content": "<|reserved_298|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "309": { + "content": "<|reserved_299|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "310": { + "content": "<|reserved_300|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "311": { + "content": "<|reserved_301|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "312": { + "content": "<|reserved_302|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "313": { + "content": "<|reserved_303|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "314": { + "content": "<|reserved_304|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "315": { + "content": "<|reserved_305|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "316": { + "content": "<|reserved_306|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "317": { + "content": "<|reserved_307|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "318": { + "content": "<|reserved_308|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "319": { + "content": "<|reserved_309|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "320": { + "content": "<|reserved_310|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "321": { + "content": "<|reserved_311|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "322": { + "content": "<|reserved_312|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "323": { + "content": "<|reserved_313|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "324": { + "content": "<|reserved_314|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "325": { + "content": "<|reserved_315|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "326": { + "content": "<|reserved_316|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "327": { + "content": "<|reserved_317|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "328": { + "content": "<|reserved_318|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "329": { + "content": "<|reserved_319|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "330": { + "content": "<|reserved_320|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "331": { + "content": "<|reserved_321|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "332": { + "content": "<|reserved_322|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "333": { + "content": "<|reserved_323|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "334": { + "content": "<|reserved_324|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "335": { + "content": "<|reserved_325|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "336": { + "content": "<|reserved_326|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "337": { + "content": "<|reserved_327|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "338": { + "content": "<|reserved_328|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "339": { + "content": "<|reserved_329|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "340": { + "content": "<|reserved_330|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "341": { + "content": "<|reserved_331|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "342": { + "content": "<|reserved_332|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "343": { + "content": "<|reserved_333|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "344": { + "content": "<|reserved_334|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "345": { + "content": "<|reserved_335|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "346": { + "content": "<|reserved_336|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "347": { + "content": "<|reserved_337|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "348": { + "content": "<|reserved_338|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "349": { + "content": "<|reserved_339|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "350": { + "content": "<|reserved_340|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "351": { + "content": "<|reserved_341|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "352": { + "content": "<|reserved_342|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "353": { + "content": "<|reserved_343|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "354": { + "content": "<|reserved_344|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "355": { + "content": "<|reserved_345|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "356": { + "content": "<|reserved_346|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "357": { + "content": "<|reserved_347|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "358": { + "content": "<|reserved_348|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "359": { + "content": "<|reserved_349|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "360": { + "content": "<|reserved_350|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "361": { + "content": "<|reserved_351|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "362": { + "content": "<|reserved_352|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "363": { + "content": "<|reserved_353|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "364": { + "content": "<|reserved_354|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "365": { + "content": "<|reserved_355|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "366": { + "content": "<|reserved_356|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "367": { + "content": "<|reserved_357|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "368": { + "content": "<|reserved_358|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "369": { + "content": "<|reserved_359|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "370": { + "content": "<|reserved_360|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "371": { + "content": "<|reserved_361|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "372": { + "content": "<|reserved_362|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "373": { + "content": "<|reserved_363|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "374": { + "content": "<|reserved_364|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "375": { + "content": "<|reserved_365|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "376": { + "content": "<|reserved_366|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "377": { + "content": "<|reserved_367|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "378": { + "content": "<|reserved_368|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "379": { + "content": "<|reserved_369|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "380": { + "content": "<|reserved_370|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "381": { + "content": "<|reserved_371|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "382": { + "content": "<|reserved_372|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "383": { + "content": "<|reserved_373|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "384": { + "content": "<|reserved_374|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "385": { + "content": "<|reserved_375|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "386": { + "content": "<|reserved_376|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "387": { + "content": "<|reserved_377|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "388": { + "content": "<|reserved_378|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "389": { + "content": "<|reserved_379|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "390": { + "content": "<|reserved_380|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "391": { + "content": "<|reserved_381|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "392": { + "content": "<|reserved_382|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "393": { + "content": "<|reserved_383|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "394": { + "content": "<|reserved_384|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "395": { + "content": "<|reserved_385|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "396": { + "content": "<|reserved_386|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "397": { + "content": "<|reserved_387|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "398": { + "content": "<|reserved_388|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "399": { + "content": "<|reserved_389|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "400": { + "content": "<|reserved_390|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "401": { + "content": "<|reserved_391|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "402": { + "content": "<|reserved_392|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "403": { + "content": "<|reserved_393|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "404": { + "content": "<|reserved_394|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "405": { + "content": "<|reserved_395|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "406": { + "content": "<|reserved_396|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "407": { + "content": "<|reserved_397|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "408": { + "content": "<|reserved_398|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "409": { + "content": "<|reserved_399|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "410": { + "content": "<|reserved_400|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "411": { + "content": "<|reserved_401|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "412": { + "content": "<|reserved_402|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "413": { + "content": "<|reserved_403|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "414": { + "content": "<|reserved_404|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "415": { + "content": "<|reserved_405|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "416": { + "content": "<|reserved_406|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "417": { + "content": "<|reserved_407|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "418": { + "content": "<|reserved_408|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "419": { + "content": "<|reserved_409|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "420": { + "content": "<|reserved_410|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "421": { + "content": "<|reserved_411|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "422": { + "content": "<|reserved_412|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "423": { + "content": "<|reserved_413|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "424": { + "content": "<|reserved_414|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "425": { + "content": "<|reserved_415|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "426": { + "content": "<|reserved_416|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "427": { + "content": "<|reserved_417|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "428": { + "content": "<|reserved_418|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "429": { + "content": "<|reserved_419|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "430": { + "content": "<|reserved_420|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "431": { + "content": "<|reserved_421|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "432": { + "content": "<|reserved_422|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "433": { + "content": "<|reserved_423|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "434": { + "content": "<|reserved_424|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "435": { + "content": "<|reserved_425|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "436": { + "content": "<|reserved_426|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "437": { + "content": "<|reserved_427|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "438": { + "content": "<|reserved_428|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "439": { + "content": "<|reserved_429|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "440": { + "content": "<|reserved_430|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "441": { + "content": "<|reserved_431|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "442": { + "content": "<|reserved_432|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "443": { + "content": "<|reserved_433|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "444": { + "content": "<|reserved_434|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "445": { + "content": "<|reserved_435|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "446": { + "content": "<|reserved_436|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "447": { + "content": "<|reserved_437|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "448": { + "content": "<|reserved_438|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "449": { + "content": "<|reserved_439|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "450": { + "content": "<|reserved_440|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "451": { + "content": "<|reserved_441|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "452": { + "content": "<|reserved_442|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "453": { + "content": "<|reserved_443|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "454": { + "content": "<|reserved_444|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "455": { + "content": "<|reserved_445|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "456": { + "content": "<|reserved_446|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "457": { + "content": "<|reserved_447|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "458": { + "content": "<|reserved_448|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "459": { + "content": "<|reserved_449|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "460": { + "content": "<|reserved_450|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "461": { + "content": "<|reserved_451|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "462": { + "content": "<|reserved_452|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "463": { + "content": "<|reserved_453|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "464": { + "content": "<|reserved_454|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "465": { + "content": "<|reserved_455|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "466": { + "content": "<|reserved_456|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "467": { + "content": "<|reserved_457|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "468": { + "content": "<|reserved_458|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "469": { + "content": "<|reserved_459|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "470": { + "content": "<|reserved_460|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "471": { + "content": "<|reserved_461|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "472": { + "content": "<|reserved_462|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "473": { + "content": "<|reserved_463|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "474": { + "content": "<|reserved_464|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "475": { + "content": "<|reserved_465|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "476": { + "content": "<|reserved_466|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "477": { + "content": "<|reserved_467|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "478": { + "content": "<|reserved_468|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "479": { + "content": "<|reserved_469|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "480": { + "content": "<|reserved_470|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "481": { + "content": "<|reserved_471|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "482": { + "content": "<|reserved_472|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "483": { + "content": "<|reserved_473|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "484": { + "content": "<|reserved_474|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "485": { + "content": "<|reserved_475|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "486": { + "content": "<|reserved_476|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "487": { + "content": "<|reserved_477|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "488": { + "content": "<|reserved_478|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "489": { + "content": "<|reserved_479|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "490": { + "content": "<|reserved_480|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "491": { + "content": "<|reserved_481|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "492": { + "content": "<|reserved_482|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "493": { + "content": "<|reserved_483|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "494": { + "content": "<|reserved_484|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "495": { + "content": "<|reserved_485|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "496": { + "content": "<|reserved_486|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "497": { + "content": "<|reserved_487|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "498": { + "content": "<|reserved_488|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "499": { + "content": "<|reserved_489|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "500": { + "content": "<|reserved_490|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64011": { + "content": "Mathias", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "64014": { + "content": "python", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "64394": { + "content": "<|cot_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64395": { + "content": "<|cot_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64396": { + "content": "<|review_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64397": { + "content": "<|review_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64398": { + "content": "<|file_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64399": { + "content": "<|file_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "legacy": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|pad|>", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast", + "use_default_system_prompt": false, + "use_fast": true +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..55732da --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bb7a6433eab5ff57ada6136013fb43bb9ab3badfabfbe02ee42ddf2ddcc9fa5 +size 10193