|
--- |
|
language: |
|
- en |
|
- ru |
|
model_creator: LakoMoor |
|
model_type: mistral |
|
license: cc-by-nc-4.0 |
|
library_name: transformers |
|
tags: |
|
- 4-bit |
|
- AWQ |
|
- text-generation |
|
- autotrain_compatible |
|
- endpoints_compatible |
|
- not-for-all-audiences |
|
- nsfw |
|
model_name: Silicon-Alice-7B |
|
base_model: |
|
- LakoMoor/Silicon-Masha-7B |
|
pipeline_tag: text-generation |
|
inference: false |
|
quantized_by: Suparious |
|
--- |
|
# LakoMoor/Silicon-Alice-7B AWQ |
|
|
|
- Model creator: [LakoMoor](https://huggingface.co./LakoMoor) |
|
- Original model: [Silicon-Alice-7B](https://huggingface.co./LakoMoor/Silicon-Alice-7B) |
|
|
|
 |
|
|
|
## Model Summary |
|
|
|
Silicon-Alice-7B is a model based on [Silicon-Masha-7B](https://huggingface.co./LakoMoor/Silicon-Alice-7B) aiming to be both strong in RP, be smart **and** understand Russian, that can follow character maps very well. This model understands Russian better than the previous one. It is suitable for RP/ERP and general use. |
|
|
|
## Prompt Template (Alpaca) |
|
|
|
I found the best SillyTavern results from using the Noromaid template but please try other templates! Let me know if you find anything good. |
|
|
|
SillyTavern config files: [Context](https://huggingface.co./LakoMoor/Silicon-Alice-7B/resolve/main/assets/context.json), [Instruct](https://huggingface.co./LakoMoor/Silicon-Alice-7B/resolve/main/assets/instruct.json). |
|
|
|
Additionally, here is my highly recommended [Text Completion preset](https://huggingface.co./LakoMoor/Silicon-Alice-7B/resolve/main/assets/MinP.json). You can tweak this by adjusting temperature up or dropping min p to boost creativity or raise min p to increase stability. You shouldn't need to touch anything else! |
|
|
|
``` |
|
Below is an instruction that describes a task. Write a response that appropriately completes the request. |
|
### Instruction: |
|
{prompt} |
|
### Response: |
|
``` |
|
|
