| # Notebook Info | |
| **Reference**: \\ | |
| - https://huggingface.co./docs/transformers/chat_templating \\ | |
| - https://github.com/MicrosoftDocs/azure-docs/blob/main/articles/ai-services/openai/includes/chat-markup-language.md \\ | |
| - https://huggingface.co./datasets/FreedomIntelligence/alpaca-gpt4-indonesian \\ | |
| - https://huggingface.co./datasets/FreedomIntelligence/sharegpt-indonesian \\ | |
| - https://huggingface.co./datasets/FreedomIntelligence/evol-instruct-indonesian \\ | |
| - https://huggingface.co./datasets/jakartaresearch/indoqa \\ | |
| **Task**: Chat or Conversational \\ | |
| **Input**: User's prompt containing chat templated text in string format \\ | |
| **Output**: Model's generated text in string format | |
| **Experiment**: | |
| - Use bos and eos token to replace <|im_start|> and <|im_end|> in ChatML. (Inspired by: https://asmirnov.xyz/doppelganger) \\ | |
| - Penggunaan padding dan truncation sesuai max_length. \\ | |
| - Max length = 256, karena telah mengkonsumsi 33.7 GB. | |