Update README.md
Browse files
README.md
CHANGED
|
@@ -148,8 +148,16 @@ This repo contains GGUF format model files for [ibm-granite/granite-3.0-8b-instr
|
|
| 148 |
|
| 149 |
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).
|
| 150 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
## Prompt template
|
| 152 |
|
|
|
|
| 153 |
```
|
| 154 |
<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|>
|
| 155 |
<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|>
|
|
@@ -160,18 +168,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 160 |
|
| 161 |
| Filename | Quant type | File Size | Description |
|
| 162 |
| -------- | ---------- | --------- | ----------- |
|
| 163 |
-
| [granite-3.0-8b-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 164 |
-
| [granite-3.0-8b-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 165 |
-
| [granite-3.0-8b-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 166 |
-
| [granite-3.0-8b-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 167 |
-
| [granite-3.0-8b-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 168 |
-
| [granite-3.0-8b-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 169 |
-
| [granite-3.0-8b-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 170 |
-
| [granite-3.0-8b-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 171 |
-
| [granite-3.0-8b-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 172 |
-
| [granite-3.0-8b-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 173 |
-
| [granite-3.0-8b-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 174 |
-
| [granite-3.0-8b-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/
|
| 175 |
|
| 176 |
|
| 177 |
## Downloading instruction
|
|
|
|
| 148 |
|
| 149 |
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).
|
| 150 |
|
| 151 |
+
|
| 152 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 153 |
+
<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;">
|
| 154 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 155 |
+
</a>
|
| 156 |
+
</div>
|
| 157 |
+
|
| 158 |
## Prompt template
|
| 159 |
|
| 160 |
+
|
| 161 |
```
|
| 162 |
<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|>
|
| 163 |
<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|>
|
|
|
|
| 168 |
|
| 169 |
| Filename | Quant type | File Size | Description |
|
| 170 |
| -------- | ---------- | --------- | ----------- |
|
| 171 |
+
| [granite-3.0-8b-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q2_K.gguf) | Q2_K | 2.890 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 172 |
+
| [granite-3.0-8b-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_S.gguf) | Q3_K_S | 3.346 GB | very small, high quality loss |
|
| 173 |
+
| [granite-3.0-8b-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_M.gguf) | Q3_K_M | 3.722 GB | very small, high quality loss |
|
| 174 |
+
| [granite-3.0-8b-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q3_K_L.gguf) | Q3_K_L | 4.051 GB | small, substantial quality loss |
|
| 175 |
+
| [granite-3.0-8b-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_0.gguf) | Q4_0 | 4.331 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 176 |
+
| [granite-3.0-8b-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_K_S.gguf) | Q4_K_S | 4.364 GB | small, greater quality loss |
|
| 177 |
+
| [granite-3.0-8b-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q4_K_M.gguf) | Q4_K_M | 4.603 GB | medium, balanced quality - recommended |
|
| 178 |
+
| [granite-3.0-8b-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q5_0.gguf) | Q5_0 | 5.259 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 179 |
+
| [granite-3.0-8b-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q5_K_S.gguf) | Q5_K_S | 5.259 GB | large, low quality loss - recommended |
|
| 180 |
+
| [granite-3.0-8b-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q5_K_M.gguf) | Q5_K_M | 5.399 GB | large, very low quality loss - recommended |
|
| 181 |
+
| [granite-3.0-8b-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q6_K.gguf) | Q6_K | 6.245 GB | very large, extremely low quality loss |
|
| 182 |
+
| [granite-3.0-8b-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/blob/main/granite-3.0-8b-instruct-Q8_0.gguf) | Q8_0 | 8.088 GB | very large, extremely low quality loss - not recommended |
|
| 183 |
|
| 184 |
|
| 185 |
## Downloading instruction
|