Duplicate from yentinglin/zh_TW_c4

Co-authored-by: Yen-Ting Lin <[email protected]>

.gitattributes

@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,193 @@
+---
+dataset_info:
+  features:
+  - name: text
+    dtype: string
+  - name: timestamp
+    dtype: string
+  - name: url
+    dtype: string
+  - name: zh_id
+    dtype: int64
+  splits:
+  - name: train
+    num_bytes: 15132113806.438198
+    num_examples: 5179546
+  - name: validation
+    num_bytes: 14820238.368907347
+    num_examples: 5099
+  download_size: 5569491261
+  dataset_size: 15146934044.807106
+license: odc-by
+task_categories:
+- text-generation
+language:
+- zh
+pretty_name: Traditional Chinese C4
+size_categories:
+- 1M<n<10M
+duplicated_from: yentinglin/zh_TW_c4
+---
+# Language Models for Taiwanese Culture 
+
+
+<p align="center">
+✍️ <a href="https://huggingface.co/spaces/yentinglin/Taiwan-LLaMa2" target="_blank">Online Demo</a>  
+•
+🤗 <a href="https://huggingface.co/yentinglin" target="_blank">HF Repo</a> • 🐦 <a href="https://twitter.com/yentinglin56" target="_blank">Twitter</a> • 📃 <a href="https://arxiv.org/pdf/2305.13711.pdf" target="_blank">[Paper Coming Soon]</a>  
+• 👨️ <a href="https://yentingl.com/" target="_blank">Yen-Ting Lin</a> 
+    <br/><br/>
+    <img src="https://www.csie.ntu.edu.tw/~miulab/taiwan-llama/logo-v2.png" width="100"> <br/>
+    <a href="https://github.com/tatsu-lab/stanford_alpaca/blob/main/LICENSE">
+<img src="https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg"></a>
+    <a href="https://github.com/tatsu-lab/stanford_alpaca/blob/main/DATA_LICENSE">
+        <img src="https://img.shields.io/badge/Data%20License-CC%20By%20NC%204.0-red.svg"></a>
+    <br/>
+   
+</p>
+
+
+
+
+## Overview
+Taiwan-LLaMa is a full parameter fine-tuned model based on LLaMa 2 for Traditional Mandarin applications.
+
+**Taiwan-LLaMa v1.0** pretrained on over 5 billion tokens and instruction-tuned on over 490k conversations both in traditional mandarin.
+
+## Demo
+A live demonstration of the model can be accessed at [Hugging Face Spaces](https://huggingface.co/spaces/yentinglin/Taiwan-LLaMa2).
+
+## Key Features
+
+1. **Traditional Mandarin Support**: The model is fine-tuned to understand and generate text in Traditional Mandarin, making it suitable for Taiwanese culture and related applications.
+
+2. **Instruction-Tuned**: Further fine-tuned on conversational data to offer context-aware and instruction-following responses.
+
+3. **Performance on Vicuna Benchmark**: Taiwan-LLaMa's relative performance on Vicuna Benchmark is measured against models like GPT-4 and ChatGPT. It's particularly optimized for Taiwanese culture.
+
+4. **Flexible Customization**: Advanced options for controlling the model's behavior like system prompt, temperature, top-p, and top-k are available in the demo.
+
+
+## Work in progress
+- [ ] **Improved pretraining**: A refined pretraining process (e.g. more data from Taiwan, training strategies) is under development, aiming to enhance model performance for better Taiwanese culture.
+- [ ] **Extend max length**: Utilizing the Rope mechanism as described in [the paper](https://arxiv.org/abs/2104.09864), the model's length will be extended from 4k to 8k.
+
+
+## Taiwanese Culture Examples
+
+| Question  | ChatGPT  | **Taiwan LLaMa v1.0**  | **Taiwan LLaMa v0.0 (w/o pretraining)**  | Llama2_Traditional_Chinese_13b_Chat  | 
+|:-|:-|:-|:-|:-|
+| 以惡地景觀著名的是高雄哪一個景點?   | 以惡地地景著名的是高雄市的旗津。    | 高雄以擁有惡地景觀著名的景點是田寮月世界。✅ | 以惡地景觀著名的是高雄市的旗津島。旗津島是一個小島，... | 高雄市內有多個以惡地景觀著名的景點，其中以下面幾個最為著名： 1. 高雄捷運紅線沿途景點：高雄市政府為了推廣高雄  |
+| 唐鳳是誰？  | 唐鳳（Audrey Tang）是台灣的政治家、社會活動家和軟體工程師。她於2016年擔任台灣行政院數位政務委員，是台灣政府歷史上首位沒有政黨背景的政務官。唐鳳在軟體工程領域有豐富的經驗。 ✅ | 唐鳳是政治評論家、資訊社會學研究者，也是台灣第一位擔任政府數位政委的人。 ✅ | 唐鳳（Tang Feng）是一位著名的中國演員和歌手。他出生於1974年12月17日，出生地點在中國北京。唐鳳在1995年開始他的演藝生涯，並在同年發行了他的首張專輯《我不孤單》。此後，他發行了許多受歡迎的歌曲，並在多部電視劇和電影中擔任主角。唐鳳因其精湛的演技和迷人的歌聲而被譽為“亞洲魅力男王”。他的音樂獲得了多個獎項，包括“華表最佳新男演唱獎”、“華表最佳歌曲獎”和“華表最佳舞蹈獎”等。  | 唐鳳是唐朝時期的一位著名文學家，他的代表作品包括《陰騭》、《狂凡子》等。他的文學風格具有強烈的個性和創意，被譽為「唐代文學之父」。  |
+| NTU 在哪?                      | NTU位於新加坡，具體地址是50 Nanyang Avenue, Singapore 639798。   | NTU 是國立臺灣大學的縮寫。它是臺灣的一所頂尖研究型大學，位於臺北市。 ✅| NTU 是台灣的一���大學，位於台北市。✅ | NTU 的總部位於台灣新北市板橋區，佔地面積約為1,000公頃。|
+| 甚麼是22K? | "22K" 可能指的是金的純度，尤其是在珠寶和金飾方面。 | "22K"是指台灣的大學畢業生的起薪，大約是新台幣22,000元。這個詞被用來形容大學畢業生的起薪偏低，並且在就業市場上對於大學畢業生的需求不足。✅| 22K是指溫度尺度上的22,000K（千度）。1K代表一度，即溫度差距，是攝氏溫標（攝氏度）的一百萬分之一。因此，22K等於-253.15°C（攝氏溫標）或-423.67°F（華氏溫標）。 |  22K是一種簡寫，即22,000。它是一個數字，表示22,000個單位。|
+| 肉圓要不要加香菜？                  | 這是個個人口味的問題，有些人喜歡在肉圓中加入香菜，因為香菜的清香可以增添風味；而有些人則不喜歡香菜的味道，覺得它會蓋過其他食材的味道。所以要不要加香菜，可以根據個人喜好來決定。 | 這是一個個人喜好的問題，有些人喜歡在肉圓裡加香菜，有些人不喜歡。**在台灣**，肉圓加香菜是一種常見的做法，這是一種在肉圓上加香菜的做法。然而，在其他國這是一個文化差異的問題。😊 | 肉圓加香菜可以增添一些芳香和美味的口感，如果你喜歡香菜的味道，可以試試加入肉圓中。香菜通常在製作過程中炒香，可以增添一些芳香和美味的味道。如果你想要加入香菜，可以在製作過程中炒香一些香菜，然後將其混入肉圓中。肉圓加香菜可以增添一些芳香和美味的口感，如果你喜歡香菜的味道，可以試試加入肉圓中。| 加香菜的肉圓味道更好，但是不加香菜的肉圓也很好吃。如果你喜歡香菜的味道，那麼加上香菜就好了。如果你不喜歡香菜，那麼不加也不會影響肉 |
+
+
+## Model
+
+We provide a number of model checkpoints that we trained. Please find them on Hugging Face [here](https://huggingface.co/models?search=taiwan-llama). Here are some quick links to the checkpoints that are finetuned from LLaMa 2:
+
+| **Model**                                              | **13B**                                                                                                                       | 
+|--------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|
+| **Taiwan-LLaMa v1.0** (_better for Taiwanese Culture_)   | 🤗 <a href="https://huggingface.co/yentinglin/Taiwan-LLaMa-v1.0" target="_blank">yentinglin/Taiwan-LLaMa-v1.0</a>  | 
+| Taiwan-LLaMa v0.9 (partial instruction set)            | 🤗 <a href="https://huggingface.co/yentinglin/Taiwan-LLaMa-v0.9" target="_blank">yentinglin/Taiwan-LLaMa-v0.9</a>  | 
+| Taiwan-LLaMa v0.0 (no Traditional Mandarin pretraining) | 🤗 <a href="https://huggingface.co/yentinglin/Taiwan-LLaMa-v0.0" target="_blank">yentinglin/Taiwan-LLaMa-v0.0</a>  | 
+
+## Data
+
+Here are some quick links to the datasets that we used to train the models:
+
+| **Dataset**                     | **Link**                                                                                                                      | 
+|---------------------------------|-------------------------------------------------------------------------------------------------------------------------------|
+| **Instruction-tuning**      | 🤗 <a href="https://huggingface.co/datasets/yentinglin/traditional_mandarin_instructions" target="_blank">yentinglin/traditional_mandarin_instructions</a>                                           | 
+| Traditional Mandarin Pretraining | 🤗 <a href="https://huggingface.co/datasets/yentinglin/zh_TW_c4" target="_blank">yentinglin/zh_TW_c4</a>                                   | 
+
+
+## Architecture
+Taiwan-LLaMa is based on LLaMa 2, leveraging transformer architecture, <a href="https://github.com/Dao-AILab/flash-attention" target="_blank">flash attention 2</a>, and bfloat16.
+
+It includes:
+
+* Pretraining Phase: Pretrained on a vast corpus of over 5 billion tokens, extracted from common crawl in Traditional Mandarin.
+* Fine-tuning Phase: Further instruction-tuned on over 490k multi-turn conversational data to enable more instruction-following and context-aware responses.
+
+## Generic Capabilities on Vicuna Benchmark 
+
+The data is translated into traditional mandarin for evaluating the general capability.
+
+
+<img src="./images/zhtw_vicuna_bench_chatgptbaseline.png" width="700">
+
+The scores are calculated with ChatGPT as the baseline, represented as 100%. The other values show the relative performance of different models compared to ChatGPT.
+
+| Language Model                      | Relative Score (%) |
+|-------------------------------------|--------------------|
+| GPT-4                               | 102.59%            |
+| ChatGPT                             | 100.00%            |
+| **Taiwan-LLaMa v1.0**               | 76.76%             |
+| Claude-Instant-1.2                  | 74.04%             |
+| Llama2_Traditional_Chinese_13b_Chat | 56.21%             |
+
+
+
+
+## How to deploy the model on my own machine?
+We recommend hosting models with [🤗 Text Generation Inference](https://github.com/huggingface/text-generation-inference). Please see their [license](https://github.com/huggingface/text-generation-inference/blob/main/LICENSE) for details on usage and limitations.
+```bash
+bash run_text_generation_inference.sh "yentinglin/Taiwan-LLaMa" NUM_GPUS DIR_TO_SAVE_MODEL PORT MAX_INPUT_LEN MODEL_MAX_LEN
+```
+
+Prompt format follows vicuna-v1.1 template:
+```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {user} ASSISTANT:
+```
+
+## Setup development environment
+```bash
+conda create -n taiwan-llama python=3.10 -y 
+conda activate taiwan-llama
+pip install -r requirements.txt
+```
+
+
+## Citations
+If you use our code, data, or models in your research, please cite this repository. You can use the following BibTeX entry:
+
+```bibtex
+@inproceedings{lin-chen-2023-llm,
+    title = "{LLM}-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models",
+    author = "Lin, Yen-Ting  and Chen, Yun-Nung",
+    booktitle = "Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)",
+    month = jul,
+    year = "2023",
+    address = "Toronto, Canada",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2023.nlp4convai-1.5",
+    pages = "47--58"
+}
+
+@misc{taiwanllama,
+    author={Lin, Yen-Ting and Chen, Yun-Nung},
+    title={Taiwanese-Aligned Language Models based on Meta-Llama2},
+    year={2023},
+    url={https://github.com/adamlin120/Taiwan-LLaMa},
+    note={Code and models available at https://github.com/adamlin120/Taiwan-LLaMa},
+}
+```
+
+## Collaborate With Us
+If you are interested in contributing to the development of Traditional Mandarin language models, exploring new applications, or leveraging Taiwan-LLaMa for your specific needs, please don't hesitate to contact us. We welcome collaborations from academia, industry, and individual contributors.
+
+## License
+The code in this project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
+
+The models included in this project are licensed under the LLAMA 2 Community License. See the [LLAMA2 License](https://github.com/facebookresearch/llama/blob/main/LICENSE) for full details.
+
+## OpenAI Data Acknowledgment
+The data included in this project were generated using OpenAI's models and are subject to OpenAI's Terms of Use. Please review [OpenAI's Terms of Use](https://openai.com/policies/terms-of-use) for details on usage and limitations.
+
+
+## Acknowledgements
+
+We thank [Meta LLaMA team](https://github.com/facebookresearch/llama) and [Vicuna team](https://github.com/lm-sys/FastChat) for their open-source efforts in democratizing large language models.

data/train-00000-of-00031-3f39a102ab83d07c.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e74082cbf17392f892015d9bcbe20c63de191be6b7988fcba6046856d1e179c
+size 178948774

data/train-00001-of-00031-11e67f9621ccfa66.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8ad39406d0c8bb5b298ab5f7386bbb052cf18c1f19de9cdfcd2b4cbd3aaea9
+size 178775798

data/train-00002-of-00031-1f3b5f20c0c525af.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa84ccdbfba380bc2feef378d12eeee0d1701cde4cbc5b516d896e75d469554
+size 180171863

data/train-00003-of-00031-ab11b74823d4c40b.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82658cddee24cd7a630ac2753b18c9943b348013b5caea39e6e9b429045dbec2
+size 180312179

data/train-00004-of-00031-05a6f6da6e2a1cc6.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2dbcb0eff45eb2e1280c456ec535d3ab44373a2f21b72e8c3a9a3a8fed1644
+size 179238086

data/train-00005-of-00031-cee6464d907be215.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687024fdf2870549818ae9941c691c47b307c8819ab7474bc1ee7851a3ed7567
+size 179796810

data/train-00006-of-00031-f045ece455f409cb.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff302666f2ab309b15368c53ac4ed2d6bd73b5daeb8510dadf0c6cf93756d95f
+size 179357125

data/train-00007-of-00031-ea485aa4a1c5dcfd.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a089943b52653efabb40882871b60861a264c3e32854dbada66860ba429bdc5e
+size 179554494

data/train-00008-of-00031-2ca3a7cee5f537d0.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2faf10138551508323d1a9c190dfce7971e426ff72a7e50739a2adf20f7351
+size 179104074

data/train-00009-of-00031-57a79b260ac5792f.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a02953ce91be7460ec2c6ba6260effb161dcd31e038e657d545da519b450b6
+size 178844838

data/train-00010-of-00031-72af92932dcd2b1d.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537bf30657a35182277068954bfed40f25caf789695e76963a85ba57ad7ca624
+size 179996603

data/train-00011-of-00031-b2c958186bc55287.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8912374fcd4b26341ee86ddceb2ade11eee066340de46b9604aa34eb8cc4452
+size 179031687

data/train-00012-of-00031-41d2620a28387b46.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d25c3f180ca334657ef3ce36ff5bc8fd829f5b60a5604560298056aa32e3bb6
+size 179397473

data/train-00013-of-00031-8dff3f220ded66c5.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2239a78653bf0a6724fde5a034a38c47012aac63f687e6bc2f7853bd2e44423d
+size 178890297

data/train-00014-of-00031-fb36e5c9663861d9.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2cd499d8ea3b703a95eb0b98a531ea8a57895da1ce2a2acb7d30dc9ce05cce
+size 179843331

data/train-00015-of-00031-c814d9d7fdc37c63.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae91ab0c562cf6e8fa672b1daa2046567796f778da149e11e076279fea510b53
+size 179138484

data/train-00016-of-00031-5e92432cf6edae27.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f8618cc3b24c18413fd3743c06bf710f51430d0ecdbdf2fb17da403db803e3
+size 179611068

data/train-00017-of-00031-d55ea984cef78067.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc93bfc141774ecba7e79cb3d726dc40bd1e47c9d263c21315652b90dc930c6
+size 178877066

data/train-00018-of-00031-6adb3dea1d3bfaf9.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1695e612948e83524e7b4e392975b6302a84a82d341f4797cd40f5b5a799384d
+size 179849643

data/train-00019-of-00031-f58c3c1962d93e05.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1502b42af834c053cb62bf14ac0993ab2695ce16e252bb8fbe59f43ee8bcc214
+size 178743150

data/train-00020-of-00031-4f91a0fac98e5564.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f77a689cca0b5cf957e67cb5d1090f30f2bb7b02a384b8a653bee30f87e060
+size 179384546

data/train-00021-of-00031-5f1f7b7a2aa71a83.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2305e895b4672509529c4f851a8b8b290d4f53162111e19ab5d92b8ae7014c35
+size 179351392

data/train-00022-of-00031-0dcf59276dec6da4.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3be777bb73b00e9d2e9f6d0ed99b1bebc5ea95327dbb9929c6d688626466e8
+size 179715443

data/train-00023-of-00031-418d000640b51a6b.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df81831c93b0179f7ae4b2e25da8f18c06efeca2685e9948375e2c6ab918fb9
+size 180192241

data/train-00024-of-00031-b75ee6bc51581ebc.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ce6eb7414415a7559996062fa1f3f17b5922a404ef41463f21adfc096b6713
+size 179577205

data/train-00025-of-00031-0c56fb12bb38f860.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ee5d6a39d925145ef5246f88949783f44099a72db8bec8fa541dc3a05d799a
+size 179565369

data/train-00026-of-00031-700cb1cc8673fa7c.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bc004f6e67d158e52c4e16cd8a88db5e581ed67bd7dcaee315162d8b6a80c6
+size 179563815

data/train-00027-of-00031-86df88742d865995.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12fc08aeda4921dcbcccd43791777e08159f12698f1b915d40f2be5300944c5
+size 179846473

data/train-00028-of-00031-3018fba2d583eff6.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e98b7530baf3e676d575e173f370aed676a0dfe115ad242a633c80c5e4e1c9
+size 178971016

data/train-00029-of-00031-e81543082347b540.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b37d02bb68e18fbc86dc1831165576d0546105791a8b87eeec7440af4dc2c45c
+size 180821421

data/train-00030-of-00031-8e8f8b6eaf81342e.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd147faaa200fbb6bf7f34a1a5ba6e907d5f36bf68de7556e976747dcd9f6ae1
+size 179656682

data/validation-00000-of-00001-303d3d5638c1fede.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3496b64058341036528cfd3d5a597a6baab52caa6f7e476962c73ebe87d0511
+size 5362815