metadata
license: apache-2.0
datasets:
- yuyijiong/Long-Instruction-with-Paraphrasing
language:
- zh
- en
Qwen2-7B-Instruct模型在 Long-Instruction-with-Paraphrasing数据集上微调 1 epoch，提升了 long-context 能力
Eval on LongBench
long-context 能力得到提升
| dataset | Qwen2-7B-Instruct | Qwen2-7b-Instruct-paraph |
|---|---|---|
| hotpotqa | 42.79 | 49.46 |
| dureader | 24.28 | 33.94 |
| multifieldqa_en | 46.17 | 49.65 |
| multifieldqa_zh | 60.64 | 64.53 |
| passage_retrieval_en | 70.0 | 84.5 |
| passage_retrieval_zh | 56.0 | 70.0 |
| trec | 76.5 | 76.5 |
| lsht | 43.5 | 45.0 |
| Average | 52.48 | 59.20 |