初始化项目，由ModelHub XC社区提供模型
Model: AdarshSingh7647/TabRankMultiTableCoTGen Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz 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
|
||||
132
README.md
Normal file
132
README.md
Normal file
@@ -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
|
||||
---
|
||||
# TabRankMultiTableCoTGen
|
||||
|
||||
|
||||
|
||||
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 Reasoning Generation** variant.
|
||||
|
||||
## What this variant does
|
||||
|
||||
The model is trained to first write a chain of thought inside a think block and then output the ranking. It generates its own reasoning at inference time. Use this variant when you want an explanation alongside the ranking.
|
||||
|
||||
## Training data
|
||||
|
||||
This model is trained on a mix of **NQ Tables** and **MultiTabQA** which adds multi table retrieval questions. The sibling checkpoint [TabRankSingleTableCoTGen](https://huggingface.co/AdarshSingh7647/TabRankSingleTableCoTGen)
|
||||
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 | 0.861 | 0.736 | 0.784 | 0.715 |
|
||||
| TAT QA | 362 | 0.657 | 0.540 | 0.425 | 0.632 |
|
||||
| HybridQA | 500 | 0.875 | 0.791 | 0.772 | 0.849 |
|
||||
| TabFact | 500 | 0.734 | 0.670 | 0.514 | 0.785 |
|
||||
| **Mean** | | **0.782** | **0.684** | **0.624** | **0.745** |
|
||||
|
||||
## Usage with vLLM
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
repo = "AdarshSingh7647/TabRankMultiTableCoTGen"
|
||||
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/TabRankMultiTableCoTGen"
|
||||
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.
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -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 %}
|
||||
71
config.json
Normal file
71
config.json
Normal file
@@ -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
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -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"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd1c81627051f4601961469b1fac2c7d2429f505ef2bffe99325c4e1790174e0
|
||||
size 16381517208
|
||||
BIN
tabrank_task.png
Normal file
BIN
tabrank_task.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 68 KiB |
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
31
tokenizer_config.json
Normal file
31
tokenizer_config.json
Normal file
@@ -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
|
||||
}
|
||||
Reference in New Issue
Block a user