Upload CoREB-Reranker (merged Qwen3-Reranker-4B + LoRA)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,99 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-Reranker-4B
+tags:
+  - code-search
+  - reranker
+  - code-retrieval
+  - peft
+  - lora
+language:
+  - en
+  - code
+datasets:
+  - hq-bench/coreb
+pipeline_tag: text-classification
+library_name: transformers
+---
+
+[![Project Page](https://img.shields.io/badge/Project-Page-blue)](https://hq-bench.github.io/coreb-page/)
+[![arXiv](https://img.shields.io/badge/arXiv-2605.04615-b31b1b.svg)](https://arxiv.org/abs/2605.04615)
+[![Dataset](https://img.shields.io/badge/HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/hq-bench/coreb)
+[![Code](https://img.shields.io/badge/GitHub-Code-black)](https://github.com/hq-bench/coreb)
+
+# 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).
+
+## Highlights
+
+- Fine-tuned from Qwen3-Reranker-4B using LoRA (rank=16, alpha=16) on **3.1M training samples** from CoREB v202602
+- 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
+
+## Reranking Results (nDCG@10 Delta %)
+
+Reranking delta on CoREB v202603, using GemEmb-2 as the first-stage retriever:
+
+| Reranker | Text-to-Code | Code-to-Text | Code-to-Code |
+|----------|:---:|:---:|:---:|
+| Jina Reranker v2 | -8.3 | -22.4 | -8.8 |
+| Jina Reranker v3 | -2.2 | -5.0 | -0.1 |
+| Qwen3-Reranker-0.6B | -0.6 | -8.2 | -2.3 |
+| Qwen3-Reranker-4B | -0.1 | -3.2 | +3.3 |
+| **CoREB-Reranker (ours)** | **+1.5** | **+0.5** | **+4.0** |
+
+## Training Details
+
+- **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)
+- **Top-k retrieval for reranking**: 128
+
+## Usage
+
+CoREB-Reranker follows the same usage pattern as Qwen3-Reranker. Given a query and a list of candidate documents from first-stage retrieval, the reranker scores each query-document pair:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "hq-bench/coreb-code-reranker"
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
+
+# Format as Qwen3-Reranker input
+query = "binary search implementation"
+document = "def binary_search(arr, target):\n    lo, hi = 0, len(arr) - 1\n    ..."
+
+prefix = '<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n'
+suffix = "<|im_end|>\n<|im_start|>assistant\n"
+instruct = "Given a code search query, does the following code snippet match the query intent?"
+
+prompt = f"{prefix}<Instruct>: {instruct}\n<Query>: {query}\n<Document>: {document}{suffix}"
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model(**inputs)
+
+# Score is the logit difference between "yes" and "no" tokens
+yes_id = tokenizer.convert_tokens_to_ids("yes")
+no_id = tokenizer.convert_tokens_to_ids("no")
+logits = outputs.logits[0, -1, :]
+score = logits[yes_id] - logits[no_id]
+print(f"Relevance score: {score.item():.4f}")
+```
+
+For batch reranking with the CoREB evaluation pipeline, see the [CoREB repository](https://github.com/hq-bench/coreb).
+
+## Citation
+
+```bibtex
+@article{xue2026coreb,
+  title={Beyond Retrieval: A Multitask Benchmark and Reranker for Code Search},
+  author={Xue, Siqiao and Liao, Zihan and Qin, Jin and Zhang, Ziyin and Mu, Yixiang and Zhou, Fan and Yu, Hang},
+  journal={arXiv preprint arXiv:2605.04615},
+  year={2026}
+}
+```

chat_template.jinja

@@ -0,0 +1,15 @@
+{%- set instruction = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a web search query, retrieve relevant passages that answer the query") -%}
+{%- set query_text = messages | selectattr("role", "eq", "query") | map(attribute="content") | first -%}
+{%- set document_text = messages | selectattr("role", "eq", "document") | map(attribute="content") | first -%}
+<|im_start|>system
+Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>
+<|im_start|>user
+<Instruct>: {{ instruction }}
+<Query>: {{ query_text }}
+<Document>: {{ document_text }}<|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3222f8eae96b717d299dadad3099a85f35db32b3b73baa57bd6e96c02fbb35e
+size 8043615040

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}