Add Evaluation
Browse files
README.md
CHANGED
@@ -18,6 +18,24 @@ This repository provides Japanese language models trained by [SB Intuitions](htt
|
|
18 |
- Model type: Autoregressive Language Model
|
19 |
- Language(s): Japanese
|
20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
## How to use
|
22 |
|
23 |
```python
|
|
|
18 |
- Model type: Autoregressive Language Model
|
19 |
- Language(s): Japanese
|
20 |
|
21 |
+
## Evaluation in Japanese tasks
|
22 |
+
|
23 |
+
| Model | Elyza-tasks-100 | Japanese MT Bench | English MT Bench |
|
24 |
+
| ------------------------------------------------------------------------------------------------- | --------------- | ----------------- | ---------------- |
|
25 |
+
| [Qwen/Qwen2.5-0.5B-instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) | 1.53 | 2.95 | 4.98 |
|
26 |
+
| **sarashina2.2-0.5B-instruct-v0.1** | **2.38** | **4.55** | **5.09** |
|
27 |
+
| | | | |
|
28 |
+
| [Rakuten/RakutenAI-2.0-mini-instruct](https://huggingface.co/Rakuten/RakutenAI-2.0-mini-instruct) | 2.41 | 4.49 | 5.13 |
|
29 |
+
| [SakanaAI/TinySwallow-1.5B-Instruct](https://huggingface.co/SakanaAI/TinySwallow-1.5B-Instruct) | 2.81 | **5.24** | 6.31 |
|
30 |
+
| [Qwen/Qwen2.5-1.5B-instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) | 2.28 | 4.06 | **6.99** |
|
31 |
+
| [llm-jp/llm-jp-3-1.8b-instruct3](https://huggingface.co/llm-jp/llm-jp-3-1.8b-instruct3) | 2.53 | 4.62 | 4.83 |
|
32 |
+
| **sarashina2.2-1B-instruct-v0.1** | **2.88** | 5.09 | 6.46 |
|
33 |
+
| | | | |
|
34 |
+
| [google/gemma-2-2b-jpn-it](https://huggingface.co/google/gemma-2-2b-jpn-it)[^4] | 3.02 | 5.19 | 7.56 |
|
35 |
+
| [Qwen/Qwen2.5-3B-instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) | 2.99 | 5.68 | **7.88** |
|
36 |
+
| [llm-jp/llm-jp-3-3.7b-instruct3](https://huggingface.co/llm-jp/llm-jp-3-3.7b-instruct3) | 2.79 | 4.98 | 5.44 |
|
37 |
+
| **sarashina2.2-3B-instruct-v0.1** | **3.75** | **6.51** | 7.71 |
|
38 |
+
|
39 |
## How to use
|
40 |
|
41 |
```python
|