---
language:
- en
pipeline_tag: text-generation
inference: false
library_name: transformers
license: cc-by-nc-nd-4.0
tags:
- not-for-all-audiences
- TensorBlock
- GGUF
base_model: NLPark/Shi-Ci_v3-Robin
---
## NLPark/Shi-Ci_v3-Robin - GGUF
This repo contains GGUF format model files for [NLPark/Shi-Ci_v3-Robin](https://huggingface.co/NLPark/Shi-Ci_v3-Robin).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
## Prompt template
```
<|role|>system<|says|>{system_prompt}<|end|>
<|role|>user<|says|>{prompt}<|end|>
<|role|>assistant<|says|>
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Shi-Ci_v3-Robin-Q2_K.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
| [Shi-Ci_v3-Robin-Q3_K_S.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
| [Shi-Ci_v3-Robin-Q3_K_M.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
| [Shi-Ci_v3-Robin-Q3_K_L.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
| [Shi-Ci_v3-Robin-Q4_0.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Shi-Ci_v3-Robin-Q4_K_S.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
| [Shi-Ci_v3-Robin-Q4_K_M.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
| [Shi-Ci_v3-Robin-Q5_0.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Shi-Ci_v3-Robin-Q5_K_S.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
| [Shi-Ci_v3-Robin-Q5_K_M.gguf](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
| [Shi-Ci_v3-Robin-Q8_0](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q8_0) | Q6_K | 74.975 GB | very large, extremely low quality loss |
| [Shi-Ci_v3-Robin-Q6_K](https://huggingface.co/tensorblock/Shi-Ci_v3-Robin-GGUF/blob/main/Shi-Ci_v3-Robin-Q6_K) | Q8_0 | 57.888 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/Shi-Ci_v3-Robin-GGUF --include "Shi-Ci_v3-Robin-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
```shell
huggingface-cli download tensorblock/Shi-Ci_v3-Robin-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```