update scores for Nejumi leaderboard and date
Browse files
README.md
CHANGED
|
@@ -46,7 +46,7 @@ Our model achieves the highest average score, more than 3 points ahead of the ne
|
|
| 46 |
|
| 47 |
Our model achieves the highest average score, more than 4 points ahead of the next best model. We use the following commit for English LM-Harness https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463.
|
| 48 |
|
| 49 |
-
An independent evaluation by Kamata et.al. for [Nejumi LLMリーダーボード Neo](https://wandb.ai/wandb-japan/llm-leaderboard/reports/Nejumi-LLM-Neo--Vmlldzo2MTkyMTU0#総合評価) using a weighted average of [llm-jp-eval](https://github.com/llm-jp/llm-jp-eval) and [Japanese MT-bench](https://github.com/Stability-AI/FastChat/tree/jp-stable/fastchat/llm_judge) also confirms the highest performance of instruct
|
| 50 |
## Usage
|
| 51 |
|
| 52 |
```python
|
|
|
|
| 46 |
|
| 47 |
Our model achieves the highest average score, more than 4 points ahead of the next best model. We use the following commit for English LM-Harness https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463.
|
| 48 |
|
| 49 |
+
An independent evaluation by Kamata et.al. for [Nejumi LLMリーダーボード Neo](https://wandb.ai/wandb-japan/llm-leaderboard/reports/Nejumi-LLM-Neo--Vmlldzo2MTkyMTU0#総合評価) using a weighted average of [llm-jp-eval](https://github.com/llm-jp/llm-jp-eval) and [Japanese MT-bench](https://github.com/Stability-AI/FastChat/tree/jp-stable/fastchat/llm_judge) also confirms the highest performance of chat/instruct versions of RakutenAI-7B among Open LLMs of similar sizes, with a score of 0.393/0.331 respectively, as of 22nd March 2024.
|
| 50 |
## Usage
|
| 51 |
|
| 52 |
```python
|