Update README.md

README.md

@@ -13,7 +13,8 @@ pipeline_tag: text-generation
 
 * 📄[Paper](https://arxiv.org/abs/2312.11193)
 * 📚[Dataset Download](https://huggingface.co/datasets/yuyijiong/Long-Instruction-with-Paraphrasing)
-* ✨[GitHub](https://github.com/yuyijiong/train_with_paraphrasing)
+* ✨[GitHub
+](https://github.com/yuyijiong/train_with_paraphrasing)
 
 ## 训练方式
 
@@ -64,8 +65,9 @@ print(tokenizer.decode(response, skip_special_tokens=True))
 | llama3-8b-chinese-chat            | 45.88     |50.56| 68.00                |22.52| 73.00    |
 | llama3-8b-chinese-chat-32k| **47.64** |49.98| **100.00**           |**25.13**| **75.0** |
 
-### LongBench (zh)
-| model                             | dureader  | multifieldqa_zh | passage_retrieval_zh |qmsum| trec      |
-|-----------------------------------|-----------|-----------------|----------------------|--|-----------|
-| llama3-8b-chinese-chat            | 29.08     | 58.40           | 93.50                |22.52| 73.00     |
-| llama3-8b-chinese-chat-32k | **32.31** | **58.66**       | 82.50                |**25.13**| **75.00** |
+## Longbench (zh)
+
+| model                      | dureader  | multifieldqa_zh | passage_retrieval_zh | vcsum     | lsht     |
+|----------------------------|-----------|-----------------|----------------------|-----------|----------|
+| llama3-8b-chinese-chat     | 29.08     | 58.4            | 93.5                 | 14.61     | 28.25     |
+| llama3-8b-chinese-chat-32k | **32.31** | **58.66**       | 82.5                 | **16.15** | **38.5** |