Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- yuyijiong/LongData-Corpus
|
| 5 |
+
- yuyijiong/Long-Instruction-Chinese
|
| 6 |
+
language:
|
| 7 |
+
- zh
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
# 版本区别
|
| 12 |
+
| 模型 | 基座模型 | 位置插值 | 训练方式 | 训练数据 |
|
| 13 |
+
|:-------------------------:|:-----------:|:------------:|:--:|:--:|
|
| 14 |
+
| LongAlpaca-7b-16k-chinese | atom-7b | 8k->16k PI |指令微调 | 长度16k以内的多文档问答、论文总结、论文问答数据 |
|
| 15 |
+
| LongAlpaca-7b-32k-chinese | atom-7b | 8k->32k PI | 指令微调 | 长度32k以内的多文档问答、论文总结、论文问答、sharegpt数据 |
|
| 16 |
+
| LongAlpaca-7b-32k-chinese-v2 | CausalLM-7b | 8k->32k Yarn | 增量预训练+指令微调 |长度32k的中文预训练数据 + 长度32k以内的多文档多轮问答、论文多任务多轮问答、sharegpt、中英翻译数据 |
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|