|
--- |
|
datasets: |
|
- PygmalionAI/PIPPA |
|
- ludis/geepeetee4 |
|
- lemonilia/LimaRP |
|
--- |
|
|
|
## GGUF |
|
|
|
gguf quants for ludis/tsukasa-13b-qlora-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 (mistral-0.1-7b) |
|
|
|
[axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training |
|
on a 4x nvidia a40 gpu cluster. |
|
|
|
the a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/). |
|
|
|
rank 8 lora tune of mistralai/Mistral-7B-v0.1, first tuned on koishi commit 6e675d1 for one epoch then on limarp (without ponyville, lolicit, all the fallen, and eka's portal subsets) Version 2023-09-30 for 2 epochs in metharme format |
|
|
|
|
