LLM-jp（NII）Proprietary

llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1

Compare this model

A 13B parameter large language model optimized for Japanese by NII, trained on 2.1T tokens from the llm-jp-corpus v3.

Share:XHatenaLINE

Parameters

Undisclosed

Context Window

License

Proprietary

Release Date

2024-01-29

API Pricing

API pricing for this model is not yet available

Strengths

  • •Instruction-tuned for bilingual dialogue
  • •Trained on diverse conversation datasets
  • •13B parameter instruction model

Weaknesses

  • •Complex multi-dataset training history
  • •Potentially uneven language performance
  • •Large memory footprint

Use Cases

  • •Bilingual Japanese-English chatbots
  • •Instruction-following dialogue systems
  • •Cross-lingual conversational AI