Update README.md
Browse files
README.md
CHANGED
|
@@ -174,8 +174,16 @@ This repo contains GGUF format model files for [Weyaxi/Einstein-v7-Qwen2-7B](htt
|
|
| 174 |
|
| 175 |
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).
|
| 176 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
## Prompt template
|
| 178 |
|
|
|
|
| 179 |
```
|
| 180 |
<|im_start|>system
|
| 181 |
{system_prompt}<|im_end|>
|
|
@@ -188,18 +196,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 188 |
|
| 189 |
| Filename | Quant type | File Size | Description |
|
| 190 |
| -------- | ---------- | --------- | ----------- |
|
| 191 |
-
| [Einstein-v7-Qwen2-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 192 |
-
| [Einstein-v7-Qwen2-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 193 |
-
| [Einstein-v7-Qwen2-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 194 |
-
| [Einstein-v7-Qwen2-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 195 |
-
| [Einstein-v7-Qwen2-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 196 |
-
| [Einstein-v7-Qwen2-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 197 |
-
| [Einstein-v7-Qwen2-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 198 |
-
| [Einstein-v7-Qwen2-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 199 |
-
| [Einstein-v7-Qwen2-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 200 |
-
| [Einstein-v7-Qwen2-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 201 |
-
| [Einstein-v7-Qwen2-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 202 |
-
| [Einstein-v7-Qwen2-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/
|
| 203 |
|
| 204 |
|
| 205 |
## Downloading instruction
|
|
|
|
| 174 |
|
| 175 |
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).
|
| 176 |
|
| 177 |
+
|
| 178 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 179 |
+
<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;">
|
| 180 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 181 |
+
</a>
|
| 182 |
+
</div>
|
| 183 |
+
|
| 184 |
## Prompt template
|
| 185 |
|
| 186 |
+
|
| 187 |
```
|
| 188 |
<|im_start|>system
|
| 189 |
{system_prompt}<|im_end|>
|
|
|
|
| 196 |
|
| 197 |
| Filename | Quant type | File Size | Description |
|
| 198 |
| -------- | ---------- | --------- | ----------- |
|
| 199 |
+
| [Einstein-v7-Qwen2-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q2_K.gguf) | Q2_K | 2.809 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 200 |
+
| [Einstein-v7-Qwen2-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q3_K_S.gguf) | Q3_K_S | 3.253 GB | very small, high quality loss |
|
| 201 |
+
| [Einstein-v7-Qwen2-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q3_K_M.gguf) | Q3_K_M | 3.547 GB | very small, high quality loss |
|
| 202 |
+
| [Einstein-v7-Qwen2-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q3_K_L.gguf) | Q3_K_L | 3.808 GB | small, substantial quality loss |
|
| 203 |
+
| [Einstein-v7-Qwen2-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q4_0.gguf) | Q4_0 | 4.127 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 204 |
+
| [Einstein-v7-Qwen2-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q4_K_S.gguf) | Q4_K_S | 4.152 GB | small, greater quality loss |
|
| 205 |
+
| [Einstein-v7-Qwen2-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q4_K_M.gguf) | Q4_K_M | 4.361 GB | medium, balanced quality - recommended |
|
| 206 |
+
| [Einstein-v7-Qwen2-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q5_0.gguf) | Q5_0 | 4.950 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 207 |
+
| [Einstein-v7-Qwen2-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q5_K_S.gguf) | Q5_K_S | 4.950 GB | large, low quality loss - recommended |
|
| 208 |
+
| [Einstein-v7-Qwen2-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q5_K_M.gguf) | Q5_K_M | 5.071 GB | large, very low quality loss - recommended |
|
| 209 |
+
| [Einstein-v7-Qwen2-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q6_K.gguf) | Q6_K | 5.825 GB | very large, extremely low quality loss |
|
| 210 |
+
| [Einstein-v7-Qwen2-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Einstein-v7-Qwen2-7B-GGUF/blob/main/Einstein-v7-Qwen2-7B-Q8_0.gguf) | Q8_0 | 7.542 GB | very large, extremely low quality loss - not recommended |
|
| 211 |
|
| 212 |
|
| 213 |
## Downloading instruction
|