OwenArli's picture
Update README.md
30de888 verified
|
raw
history blame
1.35 kB
metadata
license: llama3.1

Based on Meta-Llama-3.1-8B-Instruct, and is governed by Meta Llama 3.1 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct

Indonesian language continued pre-trained and Formax instruct tuned model. Excels in Bahasa Indonesia while having Formax instruct characteristics.

Model Llama 3.1 yang telat di-training dengan bahasa Indonesia dan juga menggunakan dataset bergaya Formax bahasa Indonesia. Cocok untuk kebutuhan text bahasa Indonesia.

Training:

  • 8192 sequence length
  • Training duration is around 6 days on 2x3090Ti
  • 1 epoch training with a massive dataset.
  • LORA with 64-rank 128-alpha resulting in ~2% trainable weights.

Quants:

BF16: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-Indo-Formax-v1.0

GGUF: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-Indo-Formax-v1.0-GGUF

Suggested prompting strategy:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a [give it a role]. You are tasked with [give it a task]. Reply in the following format: [requested format of reply]<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>