(chronos-13b-v2 + Nous-Hermes-Llama2-13b) 75/25 merge. This offers the imaginative writing style of chronos while still retaining coherency and being capable. Outputs are long and utilize exceptional prose.
Fine-tuningDocs | Chronos Hermes 13B v2 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model |
On-demand DeploymentDocs | On-demand deployments allow you to use Chronos Hermes 13B v2 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
Chronos Hermes 13B v2 is a 13 billion parameter language model developed by Austism. It is a 75/25 merge of chronos-13b-v2 and Nous-Hermes-Llama2-13B, combining Chronos's imaginative writing style with Hermes's coherence and instruction-following capabilities.
This model is optimized for:
Its output style favors long, coherent, and stylistically rich text.
The model supports a context length of 4,096 tokens.
The full 4.1K token window is usable on Fireworks AI on-demand deployments.
The model has 13 billion parameters.
Yes. Fireworks supports LoRA-based fine-tuning on dedicated GPUs.
