Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,41 @@ pipeline_tag: text-generation
|
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
|
| 11 |
-
|
| 12 |
|
| 13 |
### Model Description
|
| 14 |
|
| 15 |
-
**Moriyasu_Qwen2_JP_7B** is a is a large language model trained by Moriyasu. Based on [Qwen/Qwen2-7B]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# Moriyasu_Qwen2_JP_7B
|
| 12 |
|
| 13 |
### Model Description
|
| 14 |
|
| 15 |
+
**Moriyasu_Qwen2_JP_7B** is a is a large language model trained by Moriyasu. Based on [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B), it has been enhanced for Japanese usage through additional pre-training and instruction tuning.
|
| 16 |
+
|
| 17 |
+
# Training Datasets
|
| 18 |
+
|
| 19 |
+
### Pre-training dataset
|
| 20 |
+
|
| 21 |
+
The model is continually pre-trained on Japanese data from the Qwen2-7b model while maintaining the model's English ability (80% Japanese, 20% English). We use about 120 billion tokens sampled from, Japanese and English Wikipedia articles, Japanese CC-100 Japanese C4, Japanese OSCAR ,The Pile, Webfined, Japanese websites, book data, mathematics and code,...
|
| 22 |
+
|
| 23 |
+
### Instruction Tuning
|
| 24 |
+
We generated about 1 million Instruction data from various methods such as generated data, translated data, and data manually tagged by humans.
|
| 25 |
+
|
| 26 |
+
# Model Performance
|
| 27 |
+
|
| 28 |
+
### JGLUE tasks
|
| 29 |
+
We used the [lm-evaluation-harness](https://github.com/Stability-AI/lm-evaluation-harness/tree/jp-stable) repo to evaluate across 8 tasks, and the results are as follows:
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|Model|JCommonsenseQA|JNLI|JMARC|JSQuAD|JAQKET-V2|XL-SUM|XWINOGRAD|MGSM|JA AVG|
|
| 33 |
+
|---|---|---|---|---|---|---|---|---|---|---|---|
|
| 34 |
+
| |4-shot|4-shot|4-shot|4-shot|1-shot|4-shot|4-shot|4-shot|5-shot|0-shot| |
|
| 35 |
+
| |EM acc|Char-F1|Char-F1|Char-F1|ROUGE-2|EM acc|BLEU|BLEU|EM acc|pass@1| |
|
| 36 |
+
| RakutenAI-7B-chat | 0.9035 | 0.2600 | 0.4619 | 0.8647 | 0.1339 | 0.2120 | 0.2667 | 0.1966 | 0.4504 | 0.2299 | 0.3980 |
|
| 37 |
+
| Qwen2-7B-Instruct | 0.8856 | 0.3902 | 0.3859 | 0.8967 | 0.1277 | 0.5720 | 0.2041 | 0.1909 | 0.5713 | **0.5683** | 0.4793 |
|
| 38 |
+
| Qwen2.5-7B-Instruct | 0.9151 | 0.4293 | 0.3910 | 0.8908 | 0.1676 | **0.6240** | 0.2108 | 0.1916 | **0.6252** | 0.5305 | 0.4976 |
|
| 39 |
+
| Tanuki-8B-dpo-v1.0 | 0.2770 | 0.2937 | 0.3710 | 0.6669 | 0.1016 | 0.4280 | 0.2385 | 0.1820 | 0.3078 | 0.2555 | 0.3122 |
|
| 40 |
+
| Llama 3 8B Instruct | 0.8785 | 0.3812 | 0.3936 | 0.8955 | 0.1273 | 0.4160 | 0.2143 | 0.2035 | 0.4719 | 0.2872 | 0.4269 |
|
| 41 |
+
| Llama 3.1 8B Instruct | 0.8829 | 0.4272 | 0.4112 | 0.8856 | 0.1481 | 0.5280 | 0.2174 | 0.1990 | 0.5086 | 0.4976 | 0.4706 |
|
| 42 |
+
| Llama 3 Youko 8B Instruct | 0.9196 | 0.4850 | 0.5178 | 0.9001 | 0.2085 | 0.4680 | 0.2559 | 0.1906 | 0.4691 | 0.2695 | 0.4684 |
|
| 43 |
+
| Llama-3-ELYZA-JP-8B | 0.9017 | 0.5124 | 0.5016 | 0.9113 | 0.1677 | 0.4600 | 0.2509 | 0.1846 | 0.4829 | 0.3811 | 0.4754 |
|
| 44 |
+
| Llama 3 heron brain 8B v0.3 | 0.9231 | 0.4933 | 0.5694 | 0.9056 | **0.2178** | 0.4560 | 0.2771 | 0.2168 | 0.4993 | 0.3177 | 0.4876 |
|
| 45 |
+
| Llama 3 Swallow 8B Instruct | 0.9178 | 0.4963 | 0.5168 | 0.9088 | 0.1296 | 0.4880 | 0.2522 | 0.2254 | 0.4835 | 0.3927 | 0.4811 |
|
| 46 |
+
| Llama 3.1 Swallow 8B Instruct v0.1| 0.9240 | **0.5874** | 0.5736 | **0.9170** | 0.1380 | 0.5080 | 0.2820 | **0.2282** | 0.5301 | 0.3665 | 0.5055 |
|
| 47 |
+
| Llama 3.1 Swallow 8B Instruct v0.2| **0.9294** | 0.5601 | **0.5988** | 0.9148 | 0.1372 | 0.5280 | **0.2878** | 0.2270 | 0.5504 | 0.4079 | **0.5141** |
|
| 48 |
+
|