OpenHermes 2 Mistral 7B
OpenHermes 2 uses about 900,000 examples, primarily synthetic instructions from public datasets.
Training and model behavior
The data was filtered and converted through ShareGPT format into ChatML for training. The model uses Mistral-7B-v0.1 and a role-based conversation template.OpenHermes 2 Mistral 7B model card
Working with this model
Practical guidance. Use the shipped chat template and evaluate system-instruction compliance. Separate model quality from the effect of a prompt copied from a demonstration.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | October 2023 |
| Access | Downloadable |
| Model identifiers | teknium/OpenHermes-2-Mistral-7B |
| Context window | 32,768 tokens Configured position limit; practical serving limits depend on the runtime. OpenHermes 2 Mistral 7B configuration |
| Base model | mistralai/Mistral-7B-v0.1OpenHermes 2 Mistral 7B model card |
| Repository license label | apache-2.0OpenHermes 2 Mistral 7B model card |
Related models
- OpenHermes 13B
Nous Research · OpenHermes
A Teknium instruction model trained on a public Hermes dataset.
Launch date 2023Downloadable - OpenHermes 2.5 Mistral 7B
Nous Research · OpenHermes
A coding-enriched continuation of OpenHermes 2.
Launch date 2023Downloadable - OpenHermes 7B
Nous Research · OpenHermes
A Teknium instruction model trained on a public Hermes dataset.
Launch date 2023Downloadable