Upload README.md
Browse files
README.md
CHANGED
|
@@ -53,7 +53,7 @@ I use A100 GPU 40GB and COLAB, when trianing.
|
|
| 53 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.7388 | 0.7626 | 0.7808 | 0.7979 |
|
| 54 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.7436 | 0.7927 | 0.8037 | 0.8259 |
|
| 55 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.7509 | 0.7899 | 0.8029 | 0.8290 |
|
| 56 |
-
| **CoT-
|
| 57 |
|
| 58 |
|
| 59 |
> Natural Language Inference (NLI; 자연어 추론 평가)
|
|
@@ -68,7 +68,7 @@ I use A100 GPU 40GB and COLAB, when trianing.
|
|
| 68 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4518 | 0.4668 | 0.4726 | 0.4828 |
|
| 69 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4562 | 0.4657 | 0.4698 | 0.4774 |
|
| 70 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.4571 | 0.4461 | 0.4371 | 0.4525 |
|
| 71 |
-
| **CoT-
|
| 72 |
|
| 73 |
|
| 74 |
> Question Answering (QA)
|
|
@@ -83,7 +83,7 @@ I use A100 GPU 40GB and COLAB, when trianing.
|
|
| 83 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.3607 | 0.6797 | 0.6801 | 0.6622 |
|
| 84 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.5786 | 0.6977 | 0.7084 | 0.7144 |
|
| 85 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.6028 | 0.6979 | 0.7016 | 0.6988 |
|
| 86 |
-
| **CoT-
|
| 87 |
|
| 88 |
|
| 89 |
> Classification
|
|
@@ -98,7 +98,7 @@ I use A100 GPU 40GB and COLAB, when trianing.
|
|
| 98 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4855 | 0.8295 | 0.8711 | 0.8513 |
|
| 99 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4594 | 0.7611 | 0.7276 | 0.9370 |
|
| 100 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.5821 | 0.7653 | 0.7991 | 0.8643 |
|
| 101 |
-
| **CoT-
|
| 102 |
|
| 103 |
|
| 104 |
# Implementation Code
|
|
|
|
| 53 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.7388 | 0.7626 | 0.7808 | 0.7979 |
|
| 54 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.7436 | 0.7927 | 0.8037 | 0.8259 |
|
| 55 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.7509 | 0.7899 | 0.8029 | 0.8290 |
|
| 56 |
+
| **CoT-llama2-7B(ours)** | 0.7528 | 0.7888 | 0.7998 | 0.8210 |
|
| 57 |
|
| 58 |
|
| 59 |
> Natural Language Inference (NLI; 자연어 추론 평가)
|
|
|
|
| 68 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4518 | 0.4668 | 0.4726 | 0.4828 |
|
| 69 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4562 | 0.4657 | 0.4698 | 0.4774 |
|
| 70 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.4571 | 0.4461 | 0.4371 | 0.4525 |
|
| 71 |
+
| **CoT-llama2-7B(ours)** | 0.4543 | 0.4554 | 0.4606 | 0.4579 |
|
| 72 |
|
| 73 |
|
| 74 |
> Question Answering (QA)
|
|
|
|
| 83 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.3607 | 0.6797 | 0.6801 | 0.6622 |
|
| 84 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.5786 | 0.6977 | 0.7084 | 0.7144 |
|
| 85 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.6028 | 0.6979 | 0.7016 | 0.6988 |
|
| 86 |
+
| **CoT-llama2-7B(ours)** | 0.5852 | 0.6947 | 0.7059 | 0.7213 |
|
| 87 |
|
| 88 |
|
| 89 |
> Classification
|
|
|
|
| 98 |
| [Llama-2-Ko-7b 20B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4855 | 0.8295 | 0.8711 | 0.8513 |
|
| 99 |
| [Llama-2-Ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b) | 0.4594 | 0.7611 | 0.7276 | 0.9370 |
|
| 100 |
| [KO-platypus2-7B-EX(ours)](https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex) | 0.5821 | 0.7653 | 0.7991 | 0.8643 |
|
| 101 |
+
| **CoT-llama2-7B(ours)** | 0.5045 | 0.8054 | 0.7942 | 0.9446 |
|
| 102 |
|
| 103 |
|
| 104 |
# Implementation Code
|