Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
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 |
+
|