LLM-jp 13B v1.1 Instruct LoRA
LLM-jp 13B v1.1 Instruct LoRA updates instruction training for the v1.0 base. It combines Dolly, OpenAssistant and ichikara 003-001 data.
Research release
English originals and Japanese instructions share the mixture
The release includes English Dolly and OpenAssistant examples, their Japanese translations, and human-written Japanese ichikara instructions. Its long repository name records those data choices.LLM-jp 13B v1.1 Instruct LoRA official model card
Load the exact base with the adapter
Practical guidance. Keep the original v1.0 base and its tokenizer when applying the adapter. Changing the base would no longer reproduce this release.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | llm-jp-13b-instruct-lora-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1 |
| Context window | 2,048 tokens Maximum sequence length stated in the model card. LLM-jp 13B v1.1 Instruct LoRA official model card |
| Base | LLM-jp 13B v1.0; 300 billion pretraining tokens.LLM-jp 13B v1.1 Instruct LoRA official model card |
| License | Apache 2.0.LLM-jp 13B v1.1 Instruct LoRA official model card |
| Distribution | LoRA adapter weights; requires the v1.0 13B base.LLM-jp v1.1 LoRA adapter files |
Related models
- LLM-jp 13B v1.0 Base
LLM-jp / NII LLMC · LLM-jp v1
The original 13B LLM-jp text model, trained on 300 billion tokens with a 2,048-token context.
Launch date not confirmedResearch releaseDownloadable - LLM-jp 13B v1.1 DPO
LLM-jp / NII LLMC · LLM-jp v1
A preference-tuned descendant of the full v1.1 instruction model using Japanese HH-RLHF data.
Launch date not confirmedResearch releaseDownloadable - LLM-jp 13B v1.1 Instruct Full
LLM-jp / NII LLMC · LLM-jp v1
The v1.1 Full instruction release combines Japanese human-written data with English and translated dialogue data.
Launch date not confirmedResearch releaseDownloadable