初始化项目，由ModelHub XC社区提供模型

Model: AdarshSingh7647/TabRankMultiTableNaive Source: Original Platform
2026-07-23 03:10:09 +08:00
commit f213c7bf80
9 changed files with 378 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,132 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- table-ranking
+- listwise-reranking
+- table-retrieval
+- table-question-answering
+- qwen3
+language:
+- en
+---
+# TabRankMultiTableNaive
+
+![task](tabrank_task.png)
+
+A single call generative listwise reranker for table retrieval built on Qwen3 8B.
+Given a question and a set of candidate tables the model returns the tables ordered
+from most to least useful for answering the question. It reads all candidates in one
+prompt and emits the full ranking in a single generation.
+
+This checkpoint is the **Single plus Multi Table Answer Only** variant.
+
+## What this variant does
+
+The model is trained to output the ranking directly. Reasoning traces were shown during training but masked from the loss so the model learns to rank without writing a chain of thought. This makes it the fastest variant at inference.
+
+## Training data
+
+This model is trained on a mix of **NQ Tables** and **MultiTabQA** which adds multi table retrieval questions. The sibling checkpoint [TabRankSingleTableNaive](https://huggingface.co/AdarshSingh7647/TabRankSingleTableNaive)
+uses the other training mix with the same objective.
+
+## Input and output format
+
+The user message lists candidate tables as blocks headed by `### Table 1` `### Table 2`
+and so on. The model returns a JSON object whose value is the ranked list of one based
+candidate positions best first:
+
+```json
+{"ranked_tables": [3, 1, 5, 2, 4]}
+```
+
+Map those positions back to your table ids to obtain the reranked list.
+
+## Evaluation
+
+Scored as a listwise reranker that reorders a first stage top 25 candidate list on four
+table question answering benchmarks. SQA and TAT QA use the full test split. HybridQA and
+TabFact use a fixed shared 500 query sample. `acc@10` counts a query correct only when every
+gold table falls inside the top 10.
+
+| Dataset | n | recall@10 | ndcg@10 | acc@10 | MRR |
+|---|---|---|---|---|---|
+| SQA | 148 | 0.878 | 0.727 | 0.818 | 0.689 |
+| TAT QA | 362 | 0.678 | 0.544 | 0.467 | 0.610 |
+| HybridQA | 500 | 0.901 | 0.788 | 0.810 | 0.818 |
+| TabFact | 500 | 0.801 | 0.719 | 0.624 | 0.807 |
+| **Mean** |  | **0.815** | **0.695** | **0.680** | **0.731** |
+
+## Usage with vLLM
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+repo = "AdarshSingh7647/TabRankMultiTableNaive"
+tok = AutoTokenizer.from_pretrained(repo)
+llm = LLM(model=repo, dtype="bfloat16", max_model_len=32768)
+
+system = ("You are a table relevance expert. Given a question and a set of candidate tables "
+          "rank them from most to least useful for answering the question. Reason in a "
+          "<think>...</think> block then output exactly JSON with key ranked_tables.")
+user = "Question: ...\n\n### Table 1\n...\n\n### Table 2\n...\n"
+
+msgs = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
+# the model outputs the ranking json directly
+out = llm.generate([text], SamplingParams(temperature=0.6, top_p=0.95, max_tokens=8192))
+print(out[0].outputs[0].text)
+```
+
+## Usage with Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo = "AdarshSingh7647/TabRankMultiTableNaive"
+tok = AutoTokenizer.from_pretrained(repo)
+model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype=torch.bfloat16, device_map="auto")
+
+system = ("You are a table relevance expert. Given a question and a set of candidate tables "
+          "rank them from most to least useful for answering the question. Reason in a "
+          "<think>...</think> block then output exactly JSON with key ranked_tables.")
+user = "Question: ...\n\n### Table 1\n...\n\n### Table 2\n...\n"
+
+msgs = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
+inputs = tok(text, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=8192, temperature=0.6, top_p=0.95, do_sample=True)
+print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
+```
+
+## Model details
+
+* Base model Qwen3 8B
+* Method LoRA rank 16 fine tuning merged into the base weights so it loads directly
+* Precision bfloat16 single file safetensors near 16 GB
+* Family the six TabRank checkpoints span three objectives (Answer Only, Reasoning Generation,
+  Reasoning Conditioned) across two training mixes (Single Table, Single plus Multi Table)
+
+## Citation
+
+The MultiTabQA data comes from RAG over Tables. Please cite it when using the Single plus
+Multi Table checkpoints:
+
+```bibtex
+@misc{zou2025ragtableshierarchicalmemory,
+      title={RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking},
+      author={Jiaru Zou and Dongqi Fu and Sirui Chen and Xinrui He and Zihao Li and Yada Zhu and Jiawei Han and Jingrui He},
+      year={2025},
+      eprint={2504.01346},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2504.01346}
+}
+```
+
+The accompanying TabRank paper is currently under review. A citation will be added here once it
+is available on arXiv.