|
--- |
|
license: mit |
|
base_model: |
|
- Qwen/Qwen2.5-Coder-7B-Instruct |
|
--- |
|
|
|
|
|
`CodeRankLLM` is a 7B LLM fine-tuned for listwise code-reranking. When combined with performant code retrievers like [`CodeRankEmbed`](https://huggingface.co/cornstack/CodeRankEmbed), it significantly enhances the quality of retrieved results for various code retrieval tasks. |
|
|
|
We release the scripts to evaluate our model's performance [here](https://github.com/gangiswag/cornstack). |
|
|
|
|
|
## Training |
|
|
|
Our code reranker is based on LLM-based listwise reranking, which has gained prominence for the ability to score multiple passages simultaneously. Training data for listwise reranking was generated by selecting 50,000 <query, positive, negatives> tuples from our high-quality dataset [CoRNStack](https://gangiswag.github.io/cornstack/), filtered to ensure higher similarity scores and better ranks for the positives. Since CoRNStack doesn't contain the ranked ordering data required for training listwise rerankers, we leverage [Qwen-2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) LLM provided ranked orderings for each example to serve as ranking supervision. We initialize our reranker with [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) and fine-tune using a language modeling objective that minimizes the prediction error of the next token in the sequence. |
