Sakana AIEvoLLM-JP
EvoLLM-JP-v1-7B
Sakana created this experimental 7B model by evolutionary merging. It combines Shisa Gamma, WizardMath and Abel checkpoints.
Research release
The chosen source models affect the license
The WizardMath ancestor makes this release different from the Apache-licensed EvoLLM-JP-A variant. The provided example uses a conversation template with Japanese instructions.EvoLLM-JP-v1-7B official model card
Working with this release
Practical guidance. Compare answers with the A variant using the same Japanese questions. Keep the license decision separate from the quality comparison.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | SakanaAI/EvoLLM-JP-v1-7B |
| Ancestry | Shisa Gamma 7B v1, WizardMath 7B V1.1 and Abel 7B 002.EvoLLM-JP-v1-7B official model card |
| Terms | Microsoft Research License Terms; the card describes a research prototype.EvoLLM-JP-v1-7B official model card |
Related models
- EvoLLM-JP-A-v1-7B
Sakana AI · EvoLLM-JP
A Japanese evolutionary merge using Arithmo2 rather than WizardMath.
Launch date not confirmedResearch releaseDownloadable - EvoLLM-JP-v1-10B
Sakana AI · EvoLLM-JP
A larger Japanese merge derived from three 7B source models.
Launch date not confirmedResearch releaseDownloadable