Update README.md
Browse files
README.md
CHANGED
@@ -35,6 +35,21 @@ Original model: https://huggingface.co/google/gemma-2-9b
|
|
35 |
| [gemma-2-9b-Q3_K_S.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q3_K_S.gguf) | Q3_K_S | 4.34GB | 7.6869 +/- 0.05373 |
|
36 |
| [gemma-2-9b-Q2_K.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q2_K.gguf) | Q2_K | 3.81GB | 8.7979 +/- 0.06191 |
|
37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
## Downloading using huggingface-cli
|
39 |
|
40 |
First, make sure you have hugginface-cli installed:
|
|
|
35 |
| [gemma-2-9b-Q3_K_S.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q3_K_S.gguf) | Q3_K_S | 4.34GB | 7.6869 +/- 0.05373 |
|
36 |
| [gemma-2-9b-Q2_K.gguf](https://huggingface.co/fedric95/gemma-2-9b-GGUF/blob/main/gemma-2-9b-Q2_K.gguf) | Q2_K | 3.81GB | 8.7979 +/- 0.06191 |
|
37 |
|
38 |
+
## Benchmark Results
|
39 |
+
|
40 |
+
| Benchmark | Quant type | Metric |
|
41 |
+
| -------- | ---------- | --------- |
|
42 |
+
| WinoGrande (0-shot) | Q8_0 | |
|
43 |
+
| WinoGrande (0-shot) | Q4_K_M | |
|
44 |
+
| WinoGrande (0-shot) | Q3_K_M | |
|
45 |
+
| WinoGrande (0-shot) | Q3_K_S | 72.6125 +/- 1.2533 |
|
46 |
+
| WinoGrande (0-shot) | Q2_K | 71.4286 +/- 1.2697 |
|
47 |
+
| HellaSwag (0-shot) | Q8_0 | |
|
48 |
+
| HellaSwag (0-shot) | Q4_K_M | |
|
49 |
+
| HellaSwag (0-shot) | Q3_K_M | |
|
50 |
+
| HellaSwag (0-shot) | Q3_K_S | 76.08046206 |
|
51 |
+
| HellaSwag (0-shot) | Q2_K | 73.07309301 |
|
52 |
+
|
53 |
## Downloading using huggingface-cli
|
54 |
|
55 |
First, make sure you have hugginface-cli installed:
|