---
license: apache-2.0
language:
- zh
- en
---
# Chinese-CodeLlama-7B-SFT-V2

We added [7k+ python code instructions](https://huggingface.co/datasets/frankminors123/Python-Code-Instructions-7k) and implemented SFT based on our [Chinese-CodeLlama-7B-SFT-V1](https://huggingface.co/frankminors123/Chinese-CodeLlama-7B-SFT-V1). Drawing on the work of [code-llama](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/), we increased 
the base period of rotary positional embeddings (RoPE) from 10000 to 1000000.

We use a sequence length of 1k for pre-training, and continue training based on this length during the fine-tuning stage. Based on a larger base period of RoPE, it can support up 15k context length extrapolation at inference time.

  Based on this [dataset](https://huggingface.co/datasets/code_search_net) (Python-test), we calculate the average of PPL on 1k length text to be 5.44. However, this value is 148.70 based on our pre-trained model.

The Chinese prompt template used is as follows:
```python
PROMPT_TEMPLATE = (
  "下面是描述一项任务的指令，并且与一则输入配对用来提供更多的上下文。请给出尽可能满足请求的回答.\n"
  "### 指令:\n{instruction}\n### 输入:\n{input}\n### 回答:\n"
)
```