| Mistral-7B finetuned on a dataset of BTS fanfic at 32k context. | |
| This model uses the alpaca format: | |
| ``` | |
| {"instruction": "An interaction between a user providing instructions, and an imaginative assistant providing responses.", "input": "...", "output": "..."} | |
| ``` | |
| Note RoPE scaling parameter **8.0**, with RoPE scaling type linear |