LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA
LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA adapts the 300-billion-token v1.0 base through LoRA. The release name identifies its instruction-data combination.
Research release
Translated dialogue data defines this variant
The release uses Dolly and OpenAssistant material translated into Japanese with DeepL. It omits Jaster from its named data combination.LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA official model card
Load the adapter with its original base
Practical guidance. Keep the original v1.0 base when loading this Dolly–OpenAssistant adapter. An adapter is not a self-contained replacement for the base model's weights.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | llm-jp-13b-instruct-lora-dolly-oasst-v1.0 |
| Context window | 2,048 tokens Maximum sequence length stated in the model card. LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA official model card |
| Base | LLM-jp 13B v1.0.LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA official model card |
| Tuning data | Dolly–OpenAssistant.LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA official model card |
| License | Apache 2.0.LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA official model card |
| Distribution | PEFT adapter release; requires the associated base model.LLM-jp 13B v1.0 Dolly–OpenAssistant LoRA official model card |
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 v1.0 Dolly–OpenAssistant Full is a distinct instruction-tuning experiment from the first LLM-jp release.
Launch date not confirmedResearch releaseDownloadable