Update README.md
Browse files
README.md
CHANGED
|
@@ -187,8 +187,16 @@ This repo contains GGUF format model files for [HuggingFaceH4/zephyr-7b-beta](ht
|
|
| 187 |
|
| 188 |
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).
|
| 189 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
## Prompt template
|
| 191 |
|
|
|
|
| 192 |
```
|
| 193 |
<|system|>
|
| 194 |
{system_prompt}</s>
|
|
@@ -201,18 +209,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 201 |
|
| 202 |
| Filename | Quant type | File Size | Description |
|
| 203 |
| -------- | ---------- | --------- | ----------- |
|
| 204 |
-
| [zephyr-7b-beta-Q2_K.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 205 |
-
| [zephyr-7b-beta-Q3_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 206 |
-
| [zephyr-7b-beta-Q3_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 207 |
-
| [zephyr-7b-beta-Q3_K_L.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 208 |
-
| [zephyr-7b-beta-Q4_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 209 |
-
| [zephyr-7b-beta-Q4_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 210 |
-
| [zephyr-7b-beta-Q4_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 211 |
-
| [zephyr-7b-beta-Q5_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 212 |
-
| [zephyr-7b-beta-Q5_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 213 |
-
| [zephyr-7b-beta-Q5_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 214 |
-
| [zephyr-7b-beta-Q6_K.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 215 |
-
| [zephyr-7b-beta-Q8_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/
|
| 216 |
|
| 217 |
|
| 218 |
## Downloading instruction
|
|
|
|
| 187 |
|
| 188 |
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).
|
| 189 |
|
| 190 |
+
|
| 191 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 192 |
+
<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;">
|
| 193 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 194 |
+
</a>
|
| 195 |
+
</div>
|
| 196 |
+
|
| 197 |
## Prompt template
|
| 198 |
|
| 199 |
+
|
| 200 |
```
|
| 201 |
<|system|>
|
| 202 |
{system_prompt}</s>
|
|
|
|
| 209 |
|
| 210 |
| Filename | Quant type | File Size | Description |
|
| 211 |
| -------- | ---------- | --------- | ----------- |
|
| 212 |
+
| [zephyr-7b-beta-Q2_K.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 213 |
+
| [zephyr-7b-beta-Q3_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
|
| 214 |
+
| [zephyr-7b-beta-Q3_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
|
| 215 |
+
| [zephyr-7b-beta-Q3_K_L.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
|
| 216 |
+
| [zephyr-7b-beta-Q4_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 217 |
+
| [zephyr-7b-beta-Q4_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
|
| 218 |
+
| [zephyr-7b-beta-Q4_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
|
| 219 |
+
| [zephyr-7b-beta-Q5_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 220 |
+
| [zephyr-7b-beta-Q5_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
|
| 221 |
+
| [zephyr-7b-beta-Q5_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
|
| 222 |
+
| [zephyr-7b-beta-Q6_K.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
|
| 223 |
+
| [zephyr-7b-beta-Q8_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/blob/main/zephyr-7b-beta-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
|
| 224 |
|
| 225 |
|
| 226 |
## Downloading instruction
|