Upload README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ license: cc-by-nc-sa-4.0
|
|
20 |
์ฌ๊ธฐ์ ๋จ์ํ ํธ๊ธฐ์ฌ์ด ๋ค์๋ค. **Upstage์์ ๋ฐํํ Depth-Up-Scaling(DUS) ๋ฐฉ๋ฒ๋ก ์ mistral-7B ๋ชจ๋ธ 2๊ฐ๋ฅผ merge(passthrough)ํ ๋ฐฉ๋ฒ**์ด๋ค.
|
21 |
์ด๋ ๋๋๊ฒ๋, DUS ๋ฐฉ๋ฒ๋ก ์ ์ ์ฉํ `upstage/SOLAR-10.7B-v1.0`๋ชจ๋ธ์ ๊ธฐ์กด์ mistral-7B ๋ชจ๋ธ๋ณด๋ค ๋ฆฌ๋๋ณด๋์์ ๋์ ์ฑ๋ฅ์ ๊ธฐ๋กํ๋ค. (์๋์ ํ
์ด๋ธ ์ฐธ๊ณ )
|
22 |
๊ทธ๋ ๋ค๋ฉด, DUS ๋ฐฉ๋ฒ๋ก ์ ์ ํ์์ด, ๋ค๋ฅธ ๋ชจ๋ธ์ ์ ์ฉํ๋ฉด ๋๊ฐ์ ๊ฒฐ๊ณผ๊ฐ ๋ฐ์ํ ์ง ๋๋ฌด๋ ๊ถ๊ธํ๋ค. ๐
|
23 |
-
|
24 |
|
25 |
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
26 |
| --- | --- | --- | --- | --- | --- | --- | --- |
|
@@ -74,7 +74,31 @@ dtype: float16
|
|
74 |
## lm-evaluation-harness(zero-shot)
|
75 |
- Follow up as [beomi/LM-Harness](https://github.com/Beomi/ko-lm-evaluation-harness)
|
76 |
```
|
77 |
-
(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
```
|
79 |
|
80 |
- Follow up as [Eleuther/LM-Harness](https://github.com/EleutherAI/lm-evaluation-harness)
|
|
|
20 |
์ฌ๊ธฐ์ ๋จ์ํ ํธ๊ธฐ์ฌ์ด ๋ค์๋ค. **Upstage์์ ๋ฐํํ Depth-Up-Scaling(DUS) ๋ฐฉ๋ฒ๋ก ์ mistral-7B ๋ชจ๋ธ 2๊ฐ๋ฅผ merge(passthrough)ํ ๋ฐฉ๋ฒ**์ด๋ค.
|
21 |
์ด๋ ๋๋๊ฒ๋, DUS ๋ฐฉ๋ฒ๋ก ์ ์ ์ฉํ `upstage/SOLAR-10.7B-v1.0`๋ชจ๋ธ์ ๊ธฐ์กด์ mistral-7B ๋ชจ๋ธ๋ณด๋ค ๋ฆฌ๋๋ณด๋์์ ๋์ ์ฑ๋ฅ์ ๊ธฐ๋กํ๋ค. (์๋์ ํ
์ด๋ธ ์ฐธ๊ณ )
|
22 |
๊ทธ๋ ๋ค๋ฉด, DUS ๋ฐฉ๋ฒ๋ก ์ ์ ํ์์ด, ๋ค๋ฅธ ๋ชจ๋ธ์ ์ ์ฉํ๋ฉด ๋๊ฐ์ ๊ฒฐ๊ณผ๊ฐ ๋ฐ์ํ ์ง ๋๋ฌด๋ ๊ถ๊ธํ๋ค. ๐
|
23 |
+
์คํ์ ํตํด์ ๋์ ํธ๊ธฐ์ฌ์ ๋ํ ๊ฒฐ๋ก ์ ๋ด๋ ค๋ณด๊ณ ์ ํ๋ค. ๐๐
|
24 |
|
25 |
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
26 |
| --- | --- | --- | --- | --- | --- | --- | --- |
|
|
|
74 |
## lm-evaluation-harness(zero-shot)
|
75 |
- Follow up as [beomi/LM-Harness](https://github.com/Beomi/ko-lm-evaluation-harness)
|
76 |
```
|
77 |
+
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
78 |
+
| Task |Version| Metric |Value | |Stderr|
|
79 |
+
|----------------|------:|--------|-----:|---|-----:|
|
80 |
+
|kobest_boolq | 0|acc |0.7201|ยฑ |0.0120|
|
81 |
+
| | |macro_f1|0.7073|ยฑ |0.0124|
|
82 |
+
|kobest_copa | 0|acc |0.6510|ยฑ |0.0151|
|
83 |
+
| | |macro_f1|0.6506|ยฑ |0.0151|
|
84 |
+
|kobest_hellaswag| 0|acc |0.4520|ยฑ |0.0223|
|
85 |
+
| | |acc_norm|0.5820|ยฑ |0.0221|
|
86 |
+
| | |macro_f1|0.4475|ยฑ |0.0222|
|
87 |
+
|kobest_sentineg | 0|acc |0.7078|ยฑ |0.0229|
|
88 |
+
| | |macro_f1|0.7071|ยฑ |0.0229|
|
89 |
+
|
90 |
+
gpt2 (pretrained=yanolja/KoSOLAR-10.7B-v0.1), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
91 |
+
| Task |Version| Metric |Value | |Stderr|
|
92 |
+
|----------------|------:|--------|-----:|---|-----:|
|
93 |
+
|kobest_boolq | 0|acc |0.8725|ยฑ |0.0089|
|
94 |
+
| | |macro_f1|0.8722|ยฑ |0.0089|
|
95 |
+
|kobest_copa | 0|acc |0.6850|ยฑ |0.0147|
|
96 |
+
| | |macro_f1|0.6844|ยฑ |0.0147|
|
97 |
+
|kobest_hellaswag| 0|acc |0.4340|ยฑ |0.0222|
|
98 |
+
| | |acc_norm|0.5840|ยฑ |0.0221|
|
99 |
+
| | |macro_f1|0.4296|ยฑ |0.0221|
|
100 |
+
|kobest_sentineg | 0|acc |0.7506|ยฑ |0.0217|
|
101 |
+
| | |macro_f1|0.7505|ยฑ |0.0217|
|
102 |
```
|
103 |
|
104 |
- Follow up as [Eleuther/LM-Harness](https://github.com/EleutherAI/lm-evaluation-harness)
|