Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- Mixtral
|
| 4 |
- instruct
|
|
@@ -12,9 +15,6 @@ tags:
|
|
| 12 |
model-index:
|
| 13 |
- name: fusedYi
|
| 14 |
results: []
|
| 15 |
-
license: apache-2.0
|
| 16 |
-
language:
|
| 17 |
-
- en
|
| 18 |
---
|
| 19 |
|
| 20 |
|
|
@@ -31,3 +31,17 @@ Yi-ceptionized.
|
|
| 31 |
|
| 32 |
1.9 x Yi-6B
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- Mixtral
|
| 7 |
- instruct
|
|
|
|
| 15 |
model-index:
|
| 16 |
- name: fusedYi
|
| 17 |
results: []
|
|
|
|
|
|
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
|
|
|
|
| 31 |
|
| 32 |
1.9 x Yi-6B
|
| 33 |
|
| 34 |
+
|
| 35 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 36 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_pharaouk__fusedyi)
|
| 37 |
+
|
| 38 |
+
| Metric |Value|
|
| 39 |
+
|---------------------------------|----:|
|
| 40 |
+
|Avg. |53.18|
|
| 41 |
+
|AI2 Reasoning Challenge (25-Shot)|55.03|
|
| 42 |
+
|HellaSwag (10-Shot) |76.60|
|
| 43 |
+
|MMLU (5-Shot) |63.43|
|
| 44 |
+
|TruthfulQA (0-shot) |49.29|
|
| 45 |
+
|Winogrande (5-shot) |72.69|
|
| 46 |
+
|GSM8k (5-shot) | 2.05|
|
| 47 |
+
|