Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- google/gemma-3-27b-it-qat
|
| 4 |
+
---
|
| 5 |
+
# gemma-3-27b-it-qat GGUF
|
| 6 |
+
|
| 7 |
+
Recommended way to run this model:
|
| 8 |
+
|
| 9 |
+
```sh
|
| 10 |
+
llama-server -hf ggml-org/gemma-3-27b-it-qat-GGUF -c 0 -fa
|
| 11 |
+
```
|
| 12 |
+
|
| 13 |
+
Then, access http://localhost:8080
|