markoarnauto
commited on
Commit
•
16f9394
1
Parent(s):
033dfe3
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -25,24 +25,24 @@ curl http://localhost:8000/v1/completions -H "Content-Type: application/json
|
|
25 |
```
|
26 |
|
27 |
## Evaluations
|
28 |
-
| __English__ | __SKLM Llama-3 70B Instruct__ | __SKLM Llama-3 70B Instruct GPTQ__ |
|
29 |
-
|
30 |
-
| Avg. | 78.17 | 76.72 |
|
31 |
-
| ARC | 74.5 | 73.0 | 71.
|
32 |
-
| Hellaswag | 79.2 | 78.0 | 77.
|
33 |
-
| MMLU | 80.8 | 79.15 |
|
34 |
-
| | | |
|
35 |
-
| __German__ | __SKLM Llama-3 70B Instruct__ | __SKLM Llama-3 70B Instruct GPTQ__ |
|
36 |
-
| Avg. | 70.83 | 69.13 |
|
37 |
-
| ARC_de | 66.7 | 65.9 |
|
38 |
-
| Hellaswag_de | 70.8 | 68.8 |
|
39 |
-
| MMLU_de | 75.0 | 72.7 |
|
40 |
-
| | | |
|
41 |
-
| __Safety__ | __SKLM Llama-3 70B Instruct__ | __SKLM Llama-3 70B Instruct GPTQ__ |
|
42 |
-
| Avg. | 65.86 | 65.94 |
|
43 |
-
| RealToxicityPrompts | 97.6 | 98.4 |
|
44 |
-
| TruthfulQA | 67.07 | 65.56 |
|
45 |
-
| CrowS | 32.92 | 33.87 |
|
46 |
|
47 |
Take with caution. We did not check for data contamination.
|
48 |
Evaluation was done using [Eval. Harness](https://github.com/EleutherAI/lm-evaluation-harness) using `limit=1000` for big datasets.
|
|
|
25 |
```
|
26 |
|
27 |
## Evaluations
|
28 |
+
| __English__ | __SKLM Llama-3 70B Instruct__ | __SKLM Llama-3 70B Instruct GPTQ__ | __Llama-3 70B Instruct__ |
|
29 |
+
|:--------------|:--------------------------------|:-------------------------------------|:---------------------------|
|
30 |
+
| Avg. | 78.17 | 76.72 | 76.19 |
|
31 |
+
| ARC | 74.5 | 73.0 | 71.6 |
|
32 |
+
| Hellaswag | 79.2 | 78.0 | 77.3 |
|
33 |
+
| MMLU | 80.8 | 79.15 | 79.66 |
|
34 |
+
| | | | |
|
35 |
+
| __German__ | __SKLM Llama-3 70B Instruct__ | __SKLM Llama-3 70B Instruct GPTQ__ | __Llama-3 70B Instruct__ |
|
36 |
+
| Avg. | 70.83 | 69.13 | 68.43 |
|
37 |
+
| ARC_de | 66.7 | 65.9 | 64.2 |
|
38 |
+
| Hellaswag_de | 70.8 | 68.8 | 67.8 |
|
39 |
+
| MMLU_de | 75.0 | 72.7 | 73.3 |
|
40 |
+
| | | | |
|
41 |
+
| __Safety__ | __SKLM Llama-3 70B Instruct__ | __SKLM Llama-3 70B Instruct GPTQ__ | __Llama-3 70B Instruct__ |
|
42 |
+
| Avg. | 65.86 | 65.94 | 64.28 |
|
43 |
+
| RealToxicityPrompts | 97.6 | 98.4 | 97.9 |
|
44 |
+
| TruthfulQA | 67.07 | 65.56 | 61.91 |
|
45 |
+
| CrowS | 32.92 | 33.87 | 33.04 |
|
46 |
|
47 |
Take with caution. We did not check for data contamination.
|
48 |
Evaluation was done using [Eval. Harness](https://github.com/EleutherAI/lm-evaluation-harness) using `limit=1000` for big datasets.
|