Nous Capybara 7B v1
Nous Capybara 7B v1 uses Amplify-Instruct, which expands seed instructions into multi-turn training conversations.
Training and model behavior
The first 7B Capybara release uses about 20,000 synthetic conversation examples. The card directs users to the later Mistral-based v1.9 release. Luigi D. led the Capybara project, with contributions to datasets and training from other Nous researchers.Nous Capybara 7B v1 model card
Working with this model
Practical guidance. Compare continuity across long conversations as well as single answers. Synthetic examples can reproduce the assumptions of the models that generated them.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | September 2023 |
| Access | Downloadable |
| Model identifiers | NousResearch/Nous-Capybara-7B-V1 |
| Context window | 4,096 tokens Configured position limit; practical serving limits depend on the runtime. Nous Capybara 7B v1 configuration |
| Base model | Llama 2 7BNous Capybara 7B v1 model card |
| Repository license label | mitNous Capybara 7B v1 model card |
Related models
- Nous Capybara 34B
Nous Research · Capybara
A conversation model trained with Nous's synthetic-data method.
Launch date November 2023Downloadable - Nous Capybara 3B v1.9
Nous Research · Capybara
A conversation model trained with Nous's synthetic-data method.
Launch date October 2023Downloadable - Nous Capybara 7B v1.9
Nous Research · Capybara
A conversation model trained with Nous's synthetic-data method.
Launch date 2023Downloadable