Update training data: mixed corpus (CoREB + CodeSearchNet + APPS + CosQA + CodeFeedback)

README.md

@@ -23,11 +23,11 @@ library_name: transformers
 
 # CoREB-Reranker
 
-**CoREB-Reranker** is a code reranker fine-tuned from [Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) via LoRA on the [CoREB](https://huggingface.co/datasets/hq-bench/coreb) benchmark training set. It is the **only reranker we evaluate that achieves consistent gains across all three code search tasks** (text-to-code, code-to-text, and code-to-code).
+**CoREB-Reranker** is a code reranker fine-tuned from [Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) via LoRA on a mixed reranker corpus. It is the **only reranker we evaluate that achieves consistent gains across all three code search tasks** (text-to-code, code-to-text, and code-to-code).
 
 ## Highlights
 
-- Fine-tuned from Qwen3-Reranker-4B using LoRA (rank=16, alpha=16) on **3.1M training samples** from CoREB v202602
+- Fine-tuned from Qwen3-Reranker-4B using LoRA (rank=16, alpha=16) on **3.1M training samples** from a mixed corpus
 - Evaluated on CoREB v202603 (problem-disjoint from training set, no data leakage)
 - Achieves **positive reranking delta on all three tasks**, unlike all off-the-shelf rerankers tested
 
@@ -48,9 +48,9 @@ Reranking delta on CoREB v202603, using GemEmb-2 as the first-stage retriever:
 - **Base model**: [Qwen/Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B)
 - **Method**: LoRA (rank=16, alpha=16, dropout=0.05)
 - **Target modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
-- **Training data**: CoREB v202602 with graded relevance qrels (rel=2 positives, rel=1 hard negatives, easy negatives sampled from corpus)
-- **Evaluation data**: CoREB v202603 (problem-disjoint from training; covers a different contest time window)
-- **Training samples**: ~3.1M (3,803 queries × ~32 candidates each, across text-to-code, code-to-text, and code-to-code tasks)
+- **Training data**: A mixed reranker corpus consisting of [CoREB v202602](https://huggingface.co/datasets/hq-bench/coreb), [CodeSearchNet](https://github.com/github/CodeSearchNet) (code-to-code, code-to-text, text-to-code), [APPS](https://github.com/hendrycks/apps), [CosQA](https://github.com/Jun-jie-Huang/CosQA), and [CodeFeedback](https://github.com/OpenCodeInterpreter/OpenCodeInterpreter) (single-turn and multi-turn). Each record is normalized into binary reranking examples (instruction, query, document, yes/no). Positives are duplicated twice; one easy negative and one hard negative are sampled per record.
+- **Evaluation data**: CoREB v202603 (problem-disjoint from CoREB v202602 training split; covers a different contest time window)
+- **Training samples**: ~3.1M binary reranking examples across text-to-code, code-to-text, and code-to-code tasks
 - **Top-k retrieval for reranking**: 128
 
 ## Usage