Update README.md
Browse files
README.md
CHANGED
@@ -10,9 +10,16 @@ base_model:
|
|
10 |
pipeline_tag: text-generation
|
11 |
---
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
-
<img src="logo.png" height=350, width=350>
|
|
|
16 |
|
17 |
|
18 |
---
|
@@ -54,7 +61,7 @@ pipeline_tag: text-generation
|
|
54 |
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
55 |
|-------------------------|-------|------|-----:|------|-----:|---|-----:|
|
56 |
|KMMLU |N/A |none | 0|acc |0.3335|± |0.0475|
|
57 |
-
|KMMLU |N/A |none | 5|acc |
|
58 |
|KoBEST-HellaSwag | 0|none | 0|acc |0.4360|± |0.0222|
|
59 |
|KoBEST-HellaSwag | 0|none | 5|acc |0.4420|± |0.0222|
|
60 |
|KoBEST-BoolQ | 0|none | 0|acc |0.5064|± |0.0133|
|
@@ -79,13 +86,12 @@ pipeline_tag: text-generation
|
|
79 |
|COPA | 1|none | 0|acc |0.8300|± |0.0378|
|
80 |
|COPA | 1|none | 5|acc |0.9100|± |0.0288|
|
81 |
|truthfulqa |N/A |none | 0|acc |0.4249|± |0.0023|
|
82 |
-
|truthfulqa |N/A |none | 5|acc |
|
83 |
|
84 |
|
85 |
---
|
86 |
|
87 |
-
|
88 |
-
## Implementation Code
|
89 |
|
90 |
```python
|
91 |
### KoSOLAR-gugutypus
|
@@ -100,4 +106,31 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
100 |
device_map='auto'
|
101 |
)
|
102 |
tokenizer = AutoTokenizer.from_pretrained(repo)
|
103 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
pipeline_tag: text-generation
|
11 |
---
|
12 |
|
13 |
+
<div align="center">
|
14 |
+
<h1>🤗 KoSOLAR-v0.2-gugutypus-10.7B ☀️</h1>
|
15 |
+
|
16 |
+
<a style="margin: 0px;" href="https://github.com/oneonlee/KoSOLAR-v0.2-gugutypus-10.7B"><img style="margin: 0.5em;" alt="GitHub" src="https://img.shields.io/badge/GitHub-181717.svg?style=flat&logo=GitHub"></a>
|
17 |
+
<a style="margin: 0px;" href="https://huggingface.co/oneonlee/KoSOLAR-v0.2-gugutypus-10.7B"><img style="margin: 0.5em;" alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Models%20on%20Hub-yellow"></a>
|
18 |
+
<a style="margin: 0px;" href="https://github.com/oneonlee/KoSOLAR-v0.2-gugutypus-10.7B/blob/main/LICENSE"><img style="margin: 0.5em;" alt="License: CC BY-NC 4.0" src="https://img.shields.io/badge/License-CC%20BY%2D%2DNC%204.0-blue.svg"></a>
|
19 |
+
<a style="margin: 0px;" href="https://doi.org/10.57967/hf/1735"><img style="margin: 0.5em;" alt="DOI" src="https://img.shields.io/badge/DOI-10.57967%2Fhf%2F1735-blue"></a>
|
20 |
|
21 |
+
<img src="logo.png" height=350, width=350>
|
22 |
+
</div>
|
23 |
|
24 |
|
25 |
---
|
|
|
61 |
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
62 |
|-------------------------|-------|------|-----:|------|-----:|---|-----:|
|
63 |
|KMMLU |N/A |none | 0|acc |0.3335|± |0.0475|
|
64 |
+
|KMMLU |N/A |none | 5|acc |0.3938|± |0.0823|
|
65 |
|KoBEST-HellaSwag | 0|none | 0|acc |0.4360|± |0.0222|
|
66 |
|KoBEST-HellaSwag | 0|none | 5|acc |0.4420|± |0.0222|
|
67 |
|KoBEST-BoolQ | 0|none | 0|acc |0.5064|± |0.0133|
|
|
|
86 |
|COPA | 1|none | 0|acc |0.8300|± |0.0378|
|
87 |
|COPA | 1|none | 5|acc |0.9100|± |0.0288|
|
88 |
|truthfulqa |N/A |none | 0|acc |0.4249|± |0.0023|
|
89 |
+
|truthfulqa |N/A |none | 5|acc | - |± | - |
|
90 |
|
91 |
|
92 |
---
|
93 |
|
94 |
+
## How to Use
|
|
|
95 |
|
96 |
```python
|
97 |
### KoSOLAR-gugutypus
|
|
|
106 |
device_map='auto'
|
107 |
)
|
108 |
tokenizer = AutoTokenizer.from_pretrained(repo)
|
109 |
+
```
|
110 |
+
|
111 |
+
---
|
112 |
+
|
113 |
+
## Citation
|
114 |
+
```
|
115 |
+
@misc {donggeon_lee_2024,
|
116 |
+
author = { {DongGeon Lee} },
|
117 |
+
title = { KoSOLAR-v0.2-gugutypus-10.7B (Revision 56841d5) },
|
118 |
+
year = 2024,
|
119 |
+
url = { https://huggingface.co/oneonlee/KoSOLAR-v0.2-gugutypus-10.7B },
|
120 |
+
doi = { 10.57967/hf/1735 },
|
121 |
+
publisher = { Hugging Face }
|
122 |
+
}
|
123 |
+
```
|
124 |
+
|
125 |
+
---
|
126 |
+
|
127 |
+
## References
|
128 |
+
- [yanolja/KoSOLAR-10.7B-v0.2](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.2)
|
129 |
+
- [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0)
|
130 |
+
- [kyujinpy/KOR-gugugu-platypus-set](https://huggingface.co/datasets/kyujinpy/KOR-gugugu-platypus-set)
|
131 |
+
- [squarelike/OpenOrca-gugugo-ko](https://huggingface.co/datasets/squarelike/OpenOrca-gugugo-ko)
|
132 |
+
- [kyujinpy/KOR-OpenOrca-Platypus-v3](https://huggingface.co/datasets/kyujinpy/KOR-OpenOrca-Platypus-v3)
|
133 |
+
- [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)
|
134 |
+
- [upstage/open-ko-llm-leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)
|
135 |
+
- [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness)
|
136 |
+
- [Beomi/ko-lm-evaluation-harness](https://github.com/Beomi/ko-lm-evaluation-harness)
|