Add merged Qwen3 8B TabRank reranker model card and task image

.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

@@ -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
+---
+# TabRankSingleTableCoTCond
+
+![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 Table Reasoning Conditioned** variant.
+
+## What this variant does
+
+The model is trained with a short reasoning hint added to the prompt and learns to produce the ranking conditioned on that guidance. It is the strongest variant in our evaluation on most datasets while staying fast at inference.
+
+## Training data
+
+This model is trained on the **NQ Tables** training split only which contains single table retrieval questions. The sibling checkpoint [TabRankMultiTableCoTCond](https://huggingface.co/AdarshSingh7647/TabRankMultiTableCoTCond)
+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 | 0.893 | 0.764 | 0.838 | 0.735 |
+| TAT QA | 362 | 0.666 | 0.546 | 0.431 | 0.637 |
+| HybridQA | 500 | 0.882 | 0.790 | 0.796 | 0.833 |
+| TabFact | 500 | 0.809 | 0.726 | 0.634 | 0.817 |
+| **Mean** |  | **0.812** | **0.707** | **0.675** | **0.755** |
+
+## Usage with vLLM
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+repo = "AdarshSingh7647/TabRankSingleTableCoTCond"
+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 writes a <think> block then the ranking json
+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/TabRankSingleTableCoTCond"
+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.

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

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": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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": false,
+  "transformers_version": "5.7.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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": "5.7.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b292a3f18c79d2c2f591f93212240793730d2f85e8d61d8902939b10486c6a7
+size 16381517208

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}