library_name: transformers
widget:
- messages:
- role: system
content: >-
Anda adalah seorang konselor karir. User akan memberi Anda seorang
individu mencari bimbingan dalam kehidupan profesional mereka, dan
tugas Anda adalah membantu mereka dalam menentukan karir apa yang
paling cocok bagi mereka berdasarkan keterampilan mereka, minat, dan
pengalaman. Anda juga harus melakukan penelitian terhadap berbagai hal
tersebut pilihan yang tersedia, jelaskan tren pasar kerja di berbagai
industri, Dan saran tentang kualifikasi mana yang akan bermanfaat
untuk mengejar bidang tertentu.
- role: user
content: Halo Say!
- role: assistant
content: Eh hai, Say ! Apa yang bisa aku bantu?
- role: user
content: >-
Saya tertarik untuk mengembangkan karir di bidang perbankan. Apa yang
dapat kamu rekomendasikan ke saya?
- messages:
- role: system
content: >-
Anda adalah asisten yang berpengetahuan luas. Bantu user sebanyak yang
Anda bisa.
- role: user
content: Bagaimana caranya menjadi lebih aktif di Bulan Puasa?
- messages:
- role: system
content: >-
Anda adalah asisten yang membantu dan memberikan tanggapan yang
cerdas.
- role: user
content: Haloooo Bund!
- role: assistant
content: Halo! Apa yang bisa saya bantu?
- role: user
content: >-
Saya perlu menu buka puasa yang segar di Bulan Ramadhan ini, makanan
khas Indonesia apa saja yang cocok untuk menu buka puasa di Bulan
Ramadhan?
- messages:
- role: system
content: >-
Anda adalah asisten yang sangat kreatif. Pengguna akan memberi Anda
tugas, yang harus Anda selesaikan dengan seluruh pengetahuan Anda.
- role: user
content: >-
Tulis latar belakang cerita novel tentang seorang wanita yang ingin
memberantas geng 9 Naga.
inference:
parameters:
max_new_tokens: 128
penalty_alpha: 0.5
top_k: 4
pipeline_tag: text-generation
tags:
- conversational
- convAI
license: apache-2.0
language:
- id
- en
datasets:
- argilla/OpenHermes2.5-dpo-binarized-alpha
- wikimedia/wikipedia
- FreedomIntelligence/evol-instruct-indonesian
Model Description
Nusantara is a series of Open Weight Language Model of Bahasa Indonesia (Indonesia language). Nusantara is based from Qwen1.5 Language Model, finetuned by domain specific of datasets. As Chat-implemented language model, Nusantara is capable to do Question-Answering and respond to instructions given in Bahasa Indonesia. Due to limited resources, only 0.8B, 1.8B, 2.7B, 4B and 7B models are available. If you're interested in funding this project for further development, specific usage, or larger parameters, please contact us.
- Finetuned by: Kalis AI
- Funded by: Self-funded
- Model type: transformer-based decoder-only language model
- Language(s): Bahasa Indonesia (id), English (en)
- License: Nusantara is licensed under Apache-2.0, but any usage of this model should comply with Qwen License
- Finetuned from model: Qwen1.5-4B
Attentions!
Due to certain circumstances, models with <4B parameters tend to hallucinate easily. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Because this model is also trained with uncensored datasets, there is the possibility of negative impacts arising from using this model. All kinds of impacts that arise as a result of using this model are entirely the responsibility of the user. The model maker is not responsible for any risks incurred.
How to Get Started with the Model
Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"kalisai/Nusantara-1.8B-Indo-Chat",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("kalisai/Nusantara-1.8B-Indo-Chat")
prompt = "Berikan saya resep memasak nasi goreng yang lezat."
messages = [
{"role": "system", "content": "Kamu adalah Nusantara, asisten AI yang pintar."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
Citation
If you use the Nusantara language model in your research or project, please cite it as:
@misc{zulfikar_aji_kusworo_2024,
title={Nusantara: A Series of Versatile Open Weight Language Model of Bahasa Indonesia},
author={Zulfikar Aji Kusworo},
publisher={Hugging Face}
journal={Hugging Face Repository},
year={2024}
url = {https://huggingface.co/kalisai}
}