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.