Text Generation
Transformers
PyTorch
Indonesian
English
mistral
conversational
Inference Endpoints
text-generation-inference
Ichsan2895 commited on
Commit
abe6a0e
1 Parent(s): 011eabc

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +97 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - wikipedia
4
+ - Ichsan2895/OASST_Top1_Indonesian
5
+ - Ichsan2895/alpaca-gpt4-indonesian
6
+ language:
7
+ - id
8
+ - en
9
+ pipeline_tag: text-generation
10
+ license: cc-by-nc-sa-4.0
11
+ ---
12
+ <div style="width: auto; margin-left: auto; margin-right: auto">
13
+ <img src="https://huggingface.co/Ichsan2895/Merak-7B-v4/resolve/main/FINAL_LOGO/6.png" alt="MERAK" style="width: 50%; min-width: 100px; display: block; margin: auto;">
14
+ </div>
15
+
16
+ # THIS IS 1st PROTOTYPE OF MERAK-7B-v5!
17
+
18
+ Merak-7B is the Large Language Model of Indonesian Language
19
+
20
+ This model is based on [Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) and fine tuned by some of Indonesia Wikipedia articles that I cleaned before.
21
+
22
+ Leveraging QLoRA (QLora: Efficient Finetuning of Quantized LLMs), Merak-7B is able to run with 16 GB VRAM. We also use DPO-Trainer for RLHF with TRL library..
23
+
24
+ Licensed under Creative Commons-By Attribution-Share Alike-Non Commercial (CC-BY-SA-NC 4.0) Merak-7B empowers AI enthusiasts, researchers alike.
25
+
26
+ Big thanks to all my friends and communities that help to build our first model. Thanks for Axolotl for a great fine tuning tool which designed to streamline the fine-tuning of various AI models.
27
+
28
+ Feel free, to ask me about the model and please share the news on your social media.
29
+
30
+ ## CITATION
31
+ ```
32
+ @software{lian2023mistralorca1
33
+ title = {MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset},
34
+ author = {Wing Lian and Bleys Goodson and Guan Wang and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
35
+ year = {2023},
36
+ publisher = {HuggingFace},
37
+ journal = {HuggingFace repository},
38
+ howpublished = {\url{https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca},
39
+ }
40
+
41
+ @misc{mukherjee2023orca,
42
+ title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
43
+ author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
44
+ year={2023},
45
+ eprint={2306.02707},
46
+ archivePrefix={arXiv},
47
+ primaryClass={cs.CL}
48
+ }
49
+
50
+ @ONLINE{wikidump,
51
+ author = "Wikimedia Foundation",
52
+ title = "Wikimedia Downloads",
53
+ url = "https://dumps.wikimedia.org"
54
+ }
55
+
56
+ @inproceedings{wolf-etal-2020-transformers,
57
+ title = "Transformers: State-of-the-Art Natural Language Processing",
58
+ author = "Thomas Wolf and Lysandre Debut and Victor Sanh and Julien Chaumond and Clement Delangue and Anthony Moi and Pierric Cistac and Tim Rault and Rémi Louf and Morgan Funtowicz and Joe Davison and Sam Shleifer and Patrick von Platen and Clara Ma and Yacine Jernite and Julien Plu and Canwen Xu and Teven Le Scao and Sylvain Gugger and Mariama Drame and Quentin Lhoest and Alexander M. Rush",
59
+ booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
60
+ month = oct,
61
+ year = "2020",
62
+ address = "Online",
63
+ publisher = "Association for Computational Linguistics",
64
+ url = "https://www.aclweb.org/anthology/2020.emnlp-demos.6",
65
+ pages = "38--45"
66
+ }
67
+
68
+ @misc{vonwerra2022trl,
69
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang},
70
+ title = {TRL: Transformer Reinforcement Learning},
71
+ year = {2020},
72
+ publisher = {GitHub},
73
+ journal = {GitHub repository},
74
+ howpublished = {\url{https://github.com/huggingface/trl}}
75
+ }
76
+
77
+ @article{dettmers2023qlora,
78
+ title = {QLoRA: Efficient Finetuning of Quantized LLMs},
79
+ author = {Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
80
+ journal = {arXiv preprint arXiv:2305.14314},
81
+ year = {2023}
82
+ }
83
+ ```
84
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
85
+
86
+ ## HOW TO CITE THIS PROJECT
87
+
88
+ If you use the Merak-7B model in your research or project, please cite it as:
89
+ ```
90
+ @article{Merak,
91
+ title={Merak-7B: The LLM for Bahasa Indonesia},
92
+ author={Muhammad Ichsan},
93
+ publisher={Hugging Face}
94
+ journal={Hugging Face Repository},
95
+ year={2023}
96
+ }
97
+ ```