Update README.md
Browse files
README.md
CHANGED
|
@@ -161,8 +161,16 @@ This repo contains GGUF format model files for [Intel/neural-chat-7b-v3-3](https
|
|
| 161 |
|
| 162 |
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).
|
| 163 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 164 |
## Prompt template
|
| 165 |
|
|
|
|
| 166 |
```
|
| 167 |
### System:
|
| 168 |
{system_prompt}
|
|
@@ -175,18 +183,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 175 |
|
| 176 |
| Filename | Quant type | File Size | Description |
|
| 177 |
| -------- | ---------- | --------- | ----------- |
|
| 178 |
-
| [neural-chat-7b-v3-3-Q2_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 179 |
-
| [neural-chat-7b-v3-3-Q3_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 180 |
-
| [neural-chat-7b-v3-3-Q3_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 181 |
-
| [neural-chat-7b-v3-3-Q3_K_L.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 182 |
-
| [neural-chat-7b-v3-3-Q4_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 183 |
-
| [neural-chat-7b-v3-3-Q4_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 184 |
-
| [neural-chat-7b-v3-3-Q4_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 185 |
-
| [neural-chat-7b-v3-3-Q5_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 186 |
-
| [neural-chat-7b-v3-3-Q5_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 187 |
-
| [neural-chat-7b-v3-3-Q5_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 188 |
-
| [neural-chat-7b-v3-3-Q6_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 189 |
-
| [neural-chat-7b-v3-3-Q8_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/
|
| 190 |
|
| 191 |
|
| 192 |
## Downloading instruction
|
|
|
|
| 161 |
|
| 162 |
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).
|
| 163 |
|
| 164 |
+
|
| 165 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 166 |
+
<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;">
|
| 167 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 168 |
+
</a>
|
| 169 |
+
</div>
|
| 170 |
+
|
| 171 |
## Prompt template
|
| 172 |
|
| 173 |
+
|
| 174 |
```
|
| 175 |
### System:
|
| 176 |
{system_prompt}
|
|
|
|
| 183 |
|
| 184 |
| Filename | Quant type | File Size | Description |
|
| 185 |
| -------- | ---------- | --------- | ----------- |
|
| 186 |
+
| [neural-chat-7b-v3-3-Q2_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 187 |
+
| [neural-chat-7b-v3-3-Q3_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
|
| 188 |
+
| [neural-chat-7b-v3-3-Q3_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
|
| 189 |
+
| [neural-chat-7b-v3-3-Q3_K_L.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
|
| 190 |
+
| [neural-chat-7b-v3-3-Q4_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 191 |
+
| [neural-chat-7b-v3-3-Q4_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
|
| 192 |
+
| [neural-chat-7b-v3-3-Q4_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
|
| 193 |
+
| [neural-chat-7b-v3-3-Q5_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 194 |
+
| [neural-chat-7b-v3-3-Q5_K_S.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
|
| 195 |
+
| [neural-chat-7b-v3-3-Q5_K_M.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
|
| 196 |
+
| [neural-chat-7b-v3-3-Q6_K.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
|
| 197 |
+
| [neural-chat-7b-v3-3-Q8_0.gguf](https://huggingface.co/tensorblock/neural-chat-7b-v3-3-GGUF/blob/main/neural-chat-7b-v3-3-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
|
| 198 |
|
| 199 |
|
| 200 |
## Downloading instruction
|