woofwolfy/Silicon-Alice-7B-Q5_K_M-GGUF-Imatrix
This model was converted to GGUF format from LakoMoor/Silicon-Alice-7B
using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
What's that?
Silicon-Alice-7B-GGUF is a quantized model based on Silicon-Masha-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. It can be run on weak samovar using llama.cpp or koboldcpp.
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, Instruct.
Additionally, here is my highly recommended Text Completion preset. 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:
- Downloads last month
- 9
Model tree for woofwolfy/Silicon-Alice-7B-Q5_K_M-GGUF-Imatrix
Base model
mistralai/Mistral-7B-v0.1