Update README.md
Browse files
README.md
CHANGED
|
@@ -221,8 +221,16 @@ This repo contains GGUF format model files for [vicgalle/ConfigurableHermes-7B](
|
|
| 221 |
|
| 222 |
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).
|
| 223 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 224 |
## Prompt template
|
| 225 |
|
|
|
|
| 226 |
```
|
| 227 |
<|im_start|>system
|
| 228 |
{system_prompt}<|im_end|>
|
|
@@ -235,18 +243,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 235 |
|
| 236 |
| Filename | Quant type | File Size | Description |
|
| 237 |
| -------- | ---------- | --------- | ----------- |
|
| 238 |
-
| [ConfigurableHermes-7B-Q2_K.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 239 |
-
| [ConfigurableHermes-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 240 |
-
| [ConfigurableHermes-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 241 |
-
| [ConfigurableHermes-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 242 |
-
| [ConfigurableHermes-7B-Q4_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 243 |
-
| [ConfigurableHermes-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 244 |
-
| [ConfigurableHermes-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 245 |
-
| [ConfigurableHermes-7B-Q5_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 246 |
-
| [ConfigurableHermes-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 247 |
-
| [ConfigurableHermes-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 248 |
-
| [ConfigurableHermes-7B-Q6_K.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 249 |
-
| [ConfigurableHermes-7B-Q8_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/
|
| 250 |
|
| 251 |
|
| 252 |
## Downloading instruction
|
|
|
|
| 221 |
|
| 222 |
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).
|
| 223 |
|
| 224 |
+
|
| 225 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 226 |
+
<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;">
|
| 227 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 228 |
+
</a>
|
| 229 |
+
</div>
|
| 230 |
+
|
| 231 |
## Prompt template
|
| 232 |
|
| 233 |
+
|
| 234 |
```
|
| 235 |
<|im_start|>system
|
| 236 |
{system_prompt}<|im_end|>
|
|
|
|
| 243 |
|
| 244 |
| Filename | Quant type | File Size | Description |
|
| 245 |
| -------- | ---------- | --------- | ----------- |
|
| 246 |
+
| [ConfigurableHermes-7B-Q2_K.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 247 |
+
| [ConfigurableHermes-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
|
| 248 |
+
| [ConfigurableHermes-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
|
| 249 |
+
| [ConfigurableHermes-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
|
| 250 |
+
| [ConfigurableHermes-7B-Q4_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 251 |
+
| [ConfigurableHermes-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
|
| 252 |
+
| [ConfigurableHermes-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
|
| 253 |
+
| [ConfigurableHermes-7B-Q5_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 254 |
+
| [ConfigurableHermes-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
|
| 255 |
+
| [ConfigurableHermes-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
|
| 256 |
+
| [ConfigurableHermes-7B-Q6_K.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
|
| 257 |
+
| [ConfigurableHermes-7B-Q8_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/blob/main/ConfigurableHermes-7B-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
|
| 258 |
|
| 259 |
|
| 260 |
## Downloading instruction
|