LLM-jp-3 7.2B Instruct3
LLM-jp-3 7.2B Instruct3 is the 7.2B preference-aligned instruction release in LLM-jp's generation-3 size series. The underlying model was exposed to 2.1 trillion pretraining tokens.
Research release
Preference data targets helpfulness and safety
Instruct3 applies DPO after supervised fine-tuning. The card names aya-ja-evol-inst for helpfulness and ac-self-inst for safety preferences. The update changes alignment, while retaining the same model size and context length.LLM-jp-3 7.2B Instruct3 official model card
Review response behavior as well as accuracy
Practical guidance. For the 7.2B model, check whether preference alignment changes both useful answers and refusals. Larger models in the series cannot establish the behavior of this checkpoint.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | llm-jp-3-7.2b-instruct3 |
| Context window | 4,096 tokens Maximum sequence length stated in the model card. LLM-jp-3 7.2B Instruct3 official model card |
| Architecture | 32 layers; hidden size 4,096; 32 attention heads.LLM-jp-3 7.2B Instruct3 official model card |
| Parameters | 7,291,269,120 total, from the card's embedding and non-embedding counts.LLM-jp-3 7.2B Instruct3 official model card |
| License | Apache 2.0; research weights.LLM-jp-3 7.2B Instruct3 official model card |
Related models
- LLM-jp-3 7.2B Base
LLM-jp / NII LLMC · LLM-jp-3
LLM-jp-3 7.2B Base is a pretrained text model with 4,096-token context and Apache 2.0 weights.
Launch date not confirmedResearch releaseDownloadable - LLM-jp-3 7.2B Instruct2
LLM-jp / NII LLMC · LLM-jp-3
LLM-jp-3 7.2B Instruct2 is a supervised instruction release with 4,096-token context and Apache 2.0 weights.
Launch date not confirmedResearch releaseDownloadable