EvoLLM Models by Sakana AI
1 model2024Up to 32k ctx
Details
ResearcherSakana AI
LicenseApache 2.0(OSI)
Commercial useCommercial use allowed
Models1
Released2024
Max context32k
About
EvoLLM is a family of language models created by Sakana AI using their Evolutionary Model Merge technique, which applies evolutionary algorithms to combine existing open-weight models into new, specialized variants. EvoLLM-JP is optimized for Japanese text generation, created by merging and evolving multiple foundation models.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view
EvoLLM-JP-v1-7BCurrent
Use when the workload needs 32k context and 7B parameters.
2024-0332k context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| EvoLLM-JP-v1-7B | Use when the workload needs 32k context and 7B parameters. | 2024-03 | 32k context7B parameters | Current |
Release Timeline
1 release group2024-03
1 current
EvoLLM-JP-v1-7B
Current32k context7B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| EvoLLM-JP-v1-7B | 2024-03 | 32k | 7B |
Frequently Asked Questions
- What is EvoLLM used for?
- EvoLLM is a family of language models created by Sakana AI using their Evolutionary Model Merge technique, which applies evolutionary algorithms to combine existing open-weight models into new, specialized variants.
- How does EvoLLM compare to Claude 3?
- EvoLLM by Sakana AI is strongest where you need its listed use cases, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. EvoLLM has 1 listed variant and reaches up to 32k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which EvoLLM model should I use?
- If price is the main constraint, use the pricing table first because EvoLLM does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate EvoLLM-JP-v1-7B with 32k context.