README.md

---
language:
- en
- ru
tags:
- not-for-all-audiences
- nsfw
base_model:
- LakoMoor/Silicon-Masha-7B
license: cc-by-nc-4.0
inference: false
library_name: transformers
model_creator: LakoMoor
model_name: Silicon-Masha-7B
model_type: mistral
---

# Silicon-Masha-7B-GGUF 
![Silicon-Masha-7B](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/resolve/main/assets/masha.png)

## What's that?

Silicon-Masha-7B-GGUF is a quantized model aiming to be both strong in RP, be smart **and** understand Russian, that can follow character maps very well.  It is suitable for RP/ERP and general use.It can be run on weak samovar using [llama.cpp](https://github.com/ggerganov/llama.cpp) or [koboldcpp](https://github.com/LostRuins/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](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/resolve/main/assets/context.json), [Instruct](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/resolve/main/assets/instruct.json).

Additionally, here is my highly recommended [Text Completion preset](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/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:
```

## Provided files

| Name | Quant method | Bits | Use case |
| ---- | ---- | ---- | ----- |
| [silicon-masha-7b.Q2_K.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q2_K.gguf) | Q2_K | 2 | smallest, significant quality loss - not recommended for most purposes |
| [silicon-masha-7b.Q3_K_M.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q3_K_M.gguf) | Q3_K_M | 3 | very small, high quality loss |
| [silicon-masha-7b.Q4_0.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q4_0.gguf) | Q4_0 | 4 | legacy; small, very high quality loss - prefer using Q3_K_M |
| [silicon-masha-7b.Q4_K_M.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q4_K_M.gguf) | Q4_K_M | 4 | medium, balanced quality - recommended |
| [silicon-masha-7b.Q5_0.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q5_0.gguf) | Q5_0 | 5 | legacy; medium, balanced quality - prefer using Q4_K_M |
| [silicon-masha-7b.Q5_K_M.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q5_K_M.gguf) | Q5_K_M | 5 | large, very low quality loss - recommended |
| [silicon-masha-7b.Q6_K.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q6_K.gguf) | Q6_K | 6 | very large, extremely low quality loss |
| [silicon-masha-7b.Q8_0.gguf](https://huggingface.co/LakoMoor/Silicon-Masha-7B-GGUF/blob/main/silicon-masha-7b.Q8_0.gguf) | Q8_0 | 8 | very large, extremely low quality loss - not recommended |

## How run it ?
[llama.cpp](https://github.com/ggerganov/llama.cpp)
```shell
./main -ngl 35 -m silicon-masha-7b.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n{system_message}\n### Instruction:{prompt}\n### Response:\n"
```