|
--- |
|
datasets: |
|
- PygmalionAI/PIPPA |
|
- ludis/geepeetee4 |
|
- lemonilia/LimaRP |
|
--- |
|
|
|
## GPTQ |
|
|
|
gptq quants for ludis/tsukasa-13b-qlora-limarp download the original model except for the .bin files (or download everything and delete the .bin files) then move the contents from whichever quants folder you want to use into the original model folder and run with autogptq |
|
|
|
## Prompting |
|
|
|
https://rentry.org/v43eo - 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) |
|
|
|
then tuned on pippa for 1 epoch |
|
|
|
then tuned on ludis/geepeetee4 commit 58aabc8 for 1 epoch |
|
|
|
then tuned on limarp (without ponyville, lolicit, all the fallen, and eka's portal subsets) Version 2023-09-08 for 2 epochs |
|
|
|
|
