|
--- |
|
datasets: |
|
- PygmalionAI/PIPPA |
|
- ludis/geepeetee4 |
|
- lemonilia/LimaRP |
|
--- |
|
|
|
## Prompting |
|
|
|
https://rentry.org/tsukasa13b - reccomended prompts and gen settings |
|
|
|
The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`. |
|
|
|
The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history. |
|
|
|
## Training |
|
|
|
base model (llama-2-13b-hf) |
|
|
|
tuned on koishi dataset (commit c83d922) for 1 epoch |
|
|
|
then tuned on pippa dataset (commit 6412b0c) for 1 epoch |
|
|
|
then tuned on geepeetee4 dataset (commit c83d922) for 1 epoch |
|
|
|
then tuned on limarp (without ponyville, lolicit, and all the fallen subsets. Version 2023-09-14) for 2 epochs |
|
|
|
|
