Skip to content

Commit

Permalink
fix: typo
Browse files Browse the repository at this point in the history
  • Loading branch information
Larry0454 committed Jul 12, 2024
1 parent 7bdcd7d commit 4d23f75
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 2 deletions.
2 changes: 1 addition & 1 deletion rag/src/pipeline.py
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ def _load_vector_db(self):
def get_retrieval_content(self, query) -> str:
"""
Input: 用户提问, 是否需要rerank
ouput: 检索后并且 rerank 的内容
output: 检索后并且 rerank 的内容
"""

content = []
Expand Down
2 changes: 1 addition & 1 deletion xtuner_config/README_internlm2_7b_base_qlora.md
Original file line number Diff line number Diff line change
Expand Up @@ -138,7 +138,7 @@ model = dict(
### 数据处理

- 使用 `../datasets/process.py` 以处理 **multi_turn_dataset(12QA数据转单轮对话)**`data.json``data_pro.json` 文件(两个多轮对话),以添加或者调整 **`system` prompt**
- 使用 `../datasets/processed/process_single_turn_conversation_construction.py` 处理 **single-turn dataset** (12),修改 (`input``ouput`) ,并在每次 **conversation** 中添加 **`system` prompt**
- 使用 `../datasets/processed/process_single_turn_conversation_construction.py` 处理 **single-turn dataset** (12),修改 (`input``output`) ,并在每次 **conversation** 中添加 **`system` prompt**
- 使用 `../datasets/processed/process_merge.py` 用于合并 `../datasets/processed/` 目录下**6个更新后的数据集**,生成一个合并后的数据集 `combined_data.json`用于最终训练

## 基于XTuner的微调🎉🎉🎉🎉🎉
Expand Down

0 comments on commit 4d23f75

Please sign in to comment.