Update README.md
Browse files
README.md
CHANGED
|
@@ -130,8 +130,16 @@ This repo contains GGUF format model files for [kyujinpy/Sakura-SOLAR-Instruct](
|
|
| 130 |
|
| 131 |
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
| 132 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
## Prompt template
|
| 134 |
|
|
|
|
| 135 |
```
|
| 136 |
### System:
|
| 137 |
{system_prompt}
|
|
@@ -146,18 +154,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 146 |
|
| 147 |
| Filename | Quant type | File Size | Description |
|
| 148 |
| -------- | ---------- | --------- | ----------- |
|
| 149 |
-
| [Sakura-SOLAR-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 150 |
-
| [Sakura-SOLAR-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 151 |
-
| [Sakura-SOLAR-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 152 |
-
| [Sakura-SOLAR-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 153 |
-
| [Sakura-SOLAR-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 154 |
-
| [Sakura-SOLAR-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 155 |
-
| [Sakura-SOLAR-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 156 |
-
| [Sakura-SOLAR-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 157 |
-
| [Sakura-SOLAR-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 158 |
-
| [Sakura-SOLAR-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 159 |
-
| [Sakura-SOLAR-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 160 |
-
| [Sakura-SOLAR-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/
|
| 161 |
|
| 162 |
|
| 163 |
## Downloading instruction
|
|
|
|
| 130 |
|
| 131 |
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
| 132 |
|
| 133 |
+
|
| 134 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 135 |
+
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
| 136 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 137 |
+
</a>
|
| 138 |
+
</div>
|
| 139 |
+
|
| 140 |
## Prompt template
|
| 141 |
|
| 142 |
+
|
| 143 |
```
|
| 144 |
### System:
|
| 145 |
{system_prompt}
|
|
|
|
| 154 |
|
| 155 |
| Filename | Quant type | File Size | Description |
|
| 156 |
| -------- | ---------- | --------- | ----------- |
|
| 157 |
+
| [Sakura-SOLAR-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q2_K.gguf) | Q2_K | 3.728 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 158 |
+
| [Sakura-SOLAR-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q3_K_S.gguf) | Q3_K_S | 4.344 GB | very small, high quality loss |
|
| 159 |
+
| [Sakura-SOLAR-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q3_K_M.gguf) | Q3_K_M | 4.839 GB | very small, high quality loss |
|
| 160 |
+
| [Sakura-SOLAR-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q3_K_L.gguf) | Q3_K_L | 5.263 GB | small, substantial quality loss |
|
| 161 |
+
| [Sakura-SOLAR-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q4_0.gguf) | Q4_0 | 5.655 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 162 |
+
| [Sakura-SOLAR-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q4_K_S.gguf) | Q4_K_S | 5.698 GB | small, greater quality loss |
|
| 163 |
+
| [Sakura-SOLAR-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q4_K_M.gguf) | Q4_K_M | 6.018 GB | medium, balanced quality - recommended |
|
| 164 |
+
| [Sakura-SOLAR-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q5_0.gguf) | Q5_0 | 6.889 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 165 |
+
| [Sakura-SOLAR-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q5_K_S.gguf) | Q5_K_S | 6.889 GB | large, low quality loss - recommended |
|
| 166 |
+
| [Sakura-SOLAR-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q5_K_M.gguf) | Q5_K_M | 7.076 GB | large, very low quality loss - recommended |
|
| 167 |
+
| [Sakura-SOLAR-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q6_K.gguf) | Q6_K | 8.200 GB | very large, extremely low quality loss |
|
| 168 |
+
| [Sakura-SOLAR-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-GGUF/blob/main/Sakura-SOLAR-Instruct-Q8_0.gguf) | Q8_0 | 10.621 GB | very large, extremely low quality loss - not recommended |
|
| 169 |
|
| 170 |
|
| 171 |
## Downloading instruction
|