Sao10K: Llama 3.1 70B Hanami x1
🧠 AI Modelsao10k
Creative writing and roleplay fine-tune of Llama 3.1 70B based on Euryale v2.2.
Sao10K's Hanami x1 is a specialized fine-tuned model derived from the Llama 3.1 70B architecture, leveraging the Euryale v2.2 checkpoint. It is designed to enhance narrative generation, character dialogue, and immersive roleplay experiences. The model supports a context length of 16,000 tokens and is priced at $3 per million tokens for both input and output, making it cost-effective for lengthy interactions. It includes standard sampling parameters such as frequency_penalty, presence_penalty, repetition_penalty, and logit_bias, allowing fine-grained control over outputs. This model is part of Sao10K's experimental series, aiming to push creative AI applications.
💡Highlights
- ├─16K context length
- ├─$3/M tokens
- └─Based on Euryale v2.2
🎯For
- ├─Writers
- ├─roleplayers
- └─AI hobbyists