leaderboard-pr-bot
commited on
Commit
•
362c25c
1
Parent(s):
ca61485
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: upstage/SOLAR-10.7B-v1.0
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: yanolja/KoSOLAR-10.7B-v0.2
|
8 |
results: []
|
@@ -83,4 +83,17 @@ Our model’s training was comprehensive and diverse:
|
|
83 |
|
84 |
8. **Training Bias Towards New Tokens:** Our training data was biased to include more texts with new tokens, for effective learning.
|
85 |
|
86 |
-
This rigorous approach ensured a comprehensive and contextually rich Korean vocabulary for the model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: upstage/SOLAR-10.7B-v1.0
|
6 |
model-index:
|
7 |
- name: yanolja/KoSOLAR-10.7B-v0.2
|
8 |
results: []
|
|
|
83 |
|
84 |
8. **Training Bias Towards New Tokens:** Our training data was biased to include more texts with new tokens, for effective learning.
|
85 |
|
86 |
+
This rigorous approach ensured a comprehensive and contextually rich Korean vocabulary for the model.
|
87 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
88 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_yanolja__KoSOLAR-10.7B-v0.2)
|
89 |
+
|
90 |
+
| Metric |Value|
|
91 |
+
|---------------------------------|----:|
|
92 |
+
|Avg. |64.20|
|
93 |
+
|AI2 Reasoning Challenge (25-Shot)|61.35|
|
94 |
+
|HellaSwag (10-Shot) |82.63|
|
95 |
+
|MMLU (5-Shot) |64.85|
|
96 |
+
|TruthfulQA (0-shot) |47.94|
|
97 |
+
|Winogrande (5-shot) |80.74|
|
98 |
+
|GSM8k (5-shot) |47.69|
|
99 |
+
|