Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: gemma
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
base_model: google/gemma-2-27b-it
|
| 4 |
+
---
|
| 5 |
+
GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
|
| 6 |
+
- Original model: [gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
|
| 7 |
+
- Model creator: [Google](https://huggingface.co/google)
|
| 8 |
+
- [License](https://www.kaggle.com/models/google/gemma/license/consent?verifyToken=CfDJ8OV3w-Vr_2dIpZxXY9wVZZnpWKdFS3kJvSU2XkwpfOZICBFcOxoYJFb12HJj1BQs9FHgrjqpbEoqYjxdMwgaew-eH8JJmsLOgj56rjNeDFWaxTA36ggVQ1RJsKmH0mbl74o1qgioqSV5ktl-J5ebL9ep3JmOojU1HdBDSScB6WyGDSIuAcw8MWuy9LEE74Ze)
|
| 9 |
+
|
| 10 |
+
## Recommended Prompt Format (Gemma)
|
| 11 |
+
```
|
| 12 |
+
<start_of_turn>model
|
| 13 |
+
Provide some context and/or instructions to the model.<end_of_turn>model
|
| 14 |
+
<start_of_turn>user
|
| 15 |
+
The user’s message goes here<end_of_turn>
|
| 16 |
+
<start_of_turn>model
|
| 17 |
+
AI message goes here<end_of_turn>model
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
Quant Version: [b3450](https://github.com/ggerganov/llama.cpp/releases/tag/b3450) with [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
|