OpenHermes 13B
OpenHermes 13B uses roughly 242,000 examples from public instruction datasets. Teknium publishes the model under his own Hugging Face account.
Training and model behavior
The data mix removes two private datasets from the earlier Hermes collection. The 13B card links its public training run. The base is Llama 2.OpenHermes 13B model card
Working with this model
Practical guidance. Use the released dataset to study data provenance and reproduce the recipe. Public training examples do not remove the need to review the base model's terms.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | 2023 |
| Access | Downloadable |
| Model identifiers | teknium/OpenHermes-13B |
| Context window | 4,096 tokens Configured position limit; practical serving limits depend on the runtime. OpenHermes 13B configuration |
| Base model | Meta Llama 2 13BOpenHermes 13B model card |
| Repository license label | mitOpenHermes 13B model card |
Related models
- OpenHermes 2 Mistral 7B
Nous Research · OpenHermes
A Mistral instruction model published by Teknium.
Launch date October 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