Update README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,26 @@ language:
|
|
| 20 |
|
| 21 |
llama3.1-8b-spaetzle-v90 is a progressive merge of merges.
|
| 22 |
|
|
|
|
|
|
|
| 23 |
German EQ-Bench v2_de: 69.93 (171/171). English (v2): 77.88 (171/171)
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
The merge tree involves the following models:
|
| 26 |
|
| 27 |
- NousResearch/Hermes-3-Llama-3.1-8B
|
|
|
|
| 20 |
|
| 21 |
llama3.1-8b-spaetzle-v90 is a progressive merge of merges.
|
| 22 |
|
| 23 |
+
# evaluation
|
| 24 |
+
|
| 25 |
German EQ-Bench v2_de: 69.93 (171/171). English (v2): 77.88 (171/171)
|
| 26 |
|
| 27 |
+
[Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 28 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cstr__llama3.1-8b-spaetzle-v90)
|
| 29 |
+
|
| 30 |
+
| Metric |Value|
|
| 31 |
+
|-------------------|----:|
|
| 32 |
+
|Avg. |27.59|
|
| 33 |
+
|IFEval (0-Shot) |73.56|
|
| 34 |
+
|BBH (3-Shot) |32.76|
|
| 35 |
+
|MATH Lvl 5 (4-Shot)|13.37|
|
| 36 |
+
|GPQA (0-shot) | 4.36|
|
| 37 |
+
|MuSR (0-shot) |11.15|
|
| 38 |
+
|MMLU-PRO (5-shot) |30.34|
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
# merge tree
|
| 42 |
+
|
| 43 |
The merge tree involves the following models:
|
| 44 |
|
| 45 |
- NousResearch/Hermes-3-Llama-3.1-8B
|