初始化项目，由ModelHub XC社区提供模型

Model: riotu-lab/ArabianGPT-01B
Source: Original Platform

.gitattributes

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

LICENSE

@@ -0,0 +1,47 @@
+==========================================
+SOFTWARE LICENSE AGREEMENT - ArabianGPT
+==========================================
+
+* NAME: ArabianGPT: Advanced Language Model for Arabic Text Generation and Understanding
+
+* ACKNOWLEDGMENTS
+
+This [software] was developed by the team at [Prince Sultan University, Riyadh, Saudi Arabia] (“Owners”). 
+The statements made herein are solely the responsibility of the author[s].
+
+* LICENSE
+This software is being provided to you, the LICENSEE, by the Owners under the following license. 
+By obtaining, using, and/or copying this software, you agree that you have read, understood, and will comply with these terms and conditions. 
+Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee or royalty 
+is hereby granted, provided that you agree to comply with the following copyright notice and statements,
+including the disclaimer, and that the same appear on ALL copies of the software, documentation, 
+and modifications that you make for internal use or for distribution.
+
+> ArabianGPT Copyright 2023 by Prince Sultan University, Riyadh, Saudi Arabia. All rights reserved.
+
+If you remix, transform, or build upon the material, you must distribute your contributions under the same license as this one.
+You may not apply legal terms or technological measures that legally restrict others from doing anything this license permits.
+
+THIS SOFTWARE IS PROVIDED "AS IS" AND THE OWNERS MAKE NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED. 
+BY WAY OF EXAMPLE, BUT NOT LIMITATION, THE OWNERS MAKE NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-ABILITY OR FITNESS 
+FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE LICENSED SOFTWARE WILL NOT INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, 
+TRADEMARKS OR OTHER RIGHTS.
+
+The name of the Owners may not be used in advertising or publicity pertaining to the distribution of the software. 
+Title to copyright in this software and any associated documentation shall at all times remain with 
+the Owners and LICENSEE agrees to preserve the same.
+
+
+* CITATION
+The use of ArabianGPT should be cited as follows:
+
+@misc{ArabianGPT, 2023,
+  title={ArabianGPT: A GPT-2 Based Language Model for Arabic},
+author={Najar, Omar and Sibaee, Serry and Ghouti, Lahouari and Koubaa, Anis},
+affiliation={Prince Sultan University, Riyadh, Saudi Arabia},
+year={2023},
+}
+
+ArabianGPT Copyright 2023 by Prince Sultan University, Riyadh, Saudi Arabia. All rights reserved.
+
+===============

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+language:
+- ar
+pipeline_tag: text-generation
+tags:
+- 'arabic '
+- text-generation
+widget:
+- text: "أعلنت وزارة الحج في المملكة العربية السعودية"
+  example_title: "مثال ١"
+- text: "يبدو اليوم جميلا، سأقوم بتحضير"
+  example_title: "مثال ٢"
+- text: "إن التقنيات الحديثة"
+  example_title: "مثال ٣"
+---
+# ArabianGPT Model Overview
+
+## Disclaimer for the Use of Large Language Models (LLMs) for Text Generation
+
+<p style="color: red;">We disclaim all responsibility for any harm, inaccuracies, or inappropriate content generated by ArabianGPT-0.1B, and users engage with and apply the model's outputs at their own risk.</p>
+
+> **Important Note:** Currently, we offer a raw pre-trained model. Our team is actively working on releasing instruction-based LLMs that are fine-tuned and augmented with LRHF. The first set of pre-trained models has been made available for community exploration. While we do have models fine-tuned for specific tasks such as summarization and sentiment analysis, they are still in the development phase.
+
+
+## How you can use this Pre-Trained?
+You are invited to utilize this pre-trained, native Arabic language model as an experimental tool to assess its capabilities, aid in its fine-tuning, and evaluate its performance across a variety of downstream tasks. We encourage you to review our technical report for a comprehensive understanding of the model's performance metrics and the specific downstream tasks it has been tested on. This will provide valuable insights into its applicability and effectiveness in diverse applications.
+
+
+## Introduction
+ArabianGPT-0.1B, developed under the ArabianLLM initiatives, is a specialized GPT-2 model optimized for Arabic language modeling. 
+It's a product of the collaborative efforts at Prince Sultan University's Robotics and Internet of Things Lab, focusing on enhancing natural language modeling and generation in Arabic. 
+This model represents a significant stride in LLM research, specifically addressing the linguistic complexities and nuances of the Arabic language.
+
+## Key Features
+- **Architecture**: GPT-2
+- **Model Size**: 134 million parameters
+- **Layers**: 12
+- **Model Attention Layers (MAL)**: 12
+- **Context Window Size**: 768 tokens
+
+## Training
+- **Dataset**: Scraped Arabic newspaper articles
+- **Data Size**: 15.5 GB
+- **Words**: 237.8 million
+- **Tokenizer**: Aranizer 64K
+- **Tokens**: Over 1.75 billion
+- **Hardware**: 2 NDIVIA A100 GPUs 
+- **Training Scale**: 7.5 million examples
+- **Training Duration**: 3 days
+- **Performance**: Final loss of 3.97
+
+
+## Role in ArabianLLM Initiatives
+ArabianGPT-0.1B (Base Model) is crucial for advancing Arabic language processing, addressing challenges unique to Arabic morphology and dialects.
+
+## Usage
+Suitable for Arabic text generation tasks. Example usage with Transformers Pipeline:
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="riotu-lab/ArabianGPT-01B", max_new_tokens=512)
+text = ''
+pipe.predict(text)
+```
+
+## Limitations and Ethical Considerations
+
+- The model may have context understanding or text generation limitations in certain scenarios.
+- Emphasis on ethical use to prevent misinformation or harmful content propagation.
+
+## Acknowledgments
+
+Special thanks to Prince Sultan University, particularly the Robotics and Internet of Things Lab.
+
+## Contact Information
+
+For inquiries: [riotu@psu.edu.sa](mailto:riotu@psu.edu.sa).
+
+## Disclaimer for the Use of Large Language Models (LLMs) for Text Generation
+
+<p style="color: red;">We disclaim all responsibility for any harm, inaccuracies, or inappropriate content generated by ArabianGPT-0.1B, and users engage with and apply the model's outputs at their own risk.</p>

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 64000,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 768,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 768,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 64002
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 64000,
+  "transformers_version": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97931ddea8c30d77b7811b2c971760d064ea29a0e9b4b4ed3a88d3297eecabcf
+size 1078481861

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56b94b4242a617239256e00722f0f56924dd2eafa0c0007b93f178623b7ca06
+size 546331197

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84290731c7ca60bd4ac2da53d4ef86e0612c7fad522f3966b7fe0bf8ded9924c
+size 15597

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d011f2ad242133664d5c210e4430195460701c9035092826b29ba59ca03962aa
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4caf1d864fcff137a7c1c21f3b039dd6bb72190348ec6c92fc6584595b6fa57
+size 627

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<EOS>",
+  "pad_token": "<EOS>"
+}

tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44d489779f957d1098d4de5722bf51c6a086f0f6e57f842819279422d6d5405
+size 3451