Sponsored by
ZenMux
TIGER-Lab / StructLM-7B
Model's Last Updated: November 08 2024
text-generation
Introduction of StructLM-7B
Model Details of StructLM-7B
🏗️ StructLM: Towards Building Generalist Models for Structured Knowledge Grounding
This checkpoing seems to have some issue, please use https://huggingface.co/TIGER-Lab/StructLM-7B-Mistral instead.
Project Page: https://tiger-ai-lab.github.io/StructLM/
Paper: https://arxiv.org/pdf/2402.16671.pdf
Code: https://github.com/TIGER-AI-Lab/StructLM
Introduction
StructLM, is a series of open-source large language models (LLMs) finetuned for structured knowledge grounding (SKG) tasks. We release 3 models:
7B | StructLM-7B
13B | StructLM-13B
34B | StructLM-34B
Training Data
These models are trained on 🤗 SKGInstruct Dataset , an instruction-tuning dataset containing mixture of 19 SKG tasks combined with 🤗 SlimOrca . Check out the dataset card for more details.
Training Procedure
The models are fine-tuned with CodeLlama-Instruct-hf models as base models. Each model is trained for 3 epochs, and the best checkpoint is selected.
Evaluation
Here are a subset of model evaluation results:
Held in
| Model | ToTTo | GrailQA | CompWebQ | MMQA | Feverous | Spider | TabFact | Dart |
|---|---|---|---|---|---|---|---|---|
| StructLM-7B | 49.4 | 80.4 | 78.3 | 85.2 | 84.4 | 72.4 | 80.8 | 62.2 |
| StructLM-13B | 49.3 | 79.2 | 80.4 | 86.0 | 85.0 | 74.1 | 84.7 | 61.4 |
| StructLM-34B | 50.2 | 82.2 | 81.9 | 88.1 | 85.7 | 74.6 | 86.6 | 61.8 |
Held out
| Model | BIRD | InfoTabs | FinQA | SQA |
|---|---|---|---|---|
| StructLM-7B | 22.3 | 55.3 | 27.3 | 49.7 |
| StructLM-13B | 22.8 | 58.1 | 25.6 | 36.1 |
| StructLM-34B | 24.7 | 61.8 | 36.2 | 44.2 |
Usage
You can use the models through Huggingface's Transformers library. Check our Github repo for the evaluation code: https://github.com/TIGER-AI-Lab/StructLM
Prompt Format
For this 7B model, the prompt format (different from 13B, 34B) is
[INST] <<SYS>>
You are an AI assistant that specializes in analyzing and reasoning over structured information. You will be given a task, optionally with some structured knowledge input. Your answer must strictly adhere to the output format, if specified.
<</SYS>>
{instruction} [/INST]
To see concrete examples of this linearization, you can directly reference the 🤗 SKGInstruct Dataset (coming soon). We will provide code for linearizing this data shortly.
A few examples:
Tabular data
col : day | kilometers row 1 : tuesday | 0 row 2 : wednesday | 0 row 3 : thursday | 4 row 4 : friday | 0 row 5 : saturday | 0
Knowledge triples (dart)
Hawaii Five-O : notes : Episode: The Flight of the Jewels | [TABLECONTEXT] : [title] : Jeff Daniels | [TABLECONTEXT] : title : Hawaii Five-O
Knowledge graph schema (grailqa)
top antiquark: m.094nrqp | physics.particle_antiparticle.self_antiparticle physics.particle_family physics.particle.antiparticle physics.particle_family.subclasses physics.subatomic_particle_generation physics.particle_family.particles physics.particle common.image.appears_in_topic_gallery physics.subatomic_particle_generation.particles physics.particle.family physics.particle_family.parent_class physics.particle_antiparticle physics.particle_antiparticle.particle physics.particle.generation
Example input
[INST] <<SYS>>
You are an AI assistant that specializes in analyzing and reasoning over structured information. You will be given a task, optionally with some structured knowledge input. Your answer must strictly adhere to the output format, if specified.
<</SYS>>
Use the information in the following table to solve the problem, choose between the choices if they are provided. table:
col : day | kilometers row 1 : tuesday | 0 row 2 : wednesday | 0 row 3 : thursday | 4 row 4 : friday | 0 row 5 : saturday | 0
question:
Allie kept track of how many kilometers she walked during the past 5 days. What is the range of the numbers? [/INST]
Intended Uses
These models are trained for research purposes. They are designed to be proficient in interpreting linearized structured input. Downstream uses can potentially include various applications requiring the interpretation of structured data.
Limitations
While we've tried to build an SKG-specialized model capable of generalizing, we have shown that this is a challenging domain, and it may lack performance characteristics that allow it to be directly used in chat or other applications.
Citation
If you use the models, data, or code from this project, please cite the original paper:
@misc{zhuang2024structlm,
title={StructLM: Towards Building Generalist Models for Structured Knowledge Grounding},
author={Alex Zhuang and Ge Zhang and Tianyu Zheng and Xinrun Du and Junjie Wang and Weiming Ren and Stephen W. Huang and Jie Fu and Xiang Yue and Wenhu Chen},
year={2024},
eprint={2402.16671},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Runs of TIGER-Lab StructLM-7B on huggingface.co
29
Total runs
0
24-hour runs
-1
3-day runs
0
7-day runs
9
30-day runs
More Information About StructLM-7B huggingface.co Model
Url of StructLM-7B
StructLM-7B huggingface.co Url
Provider of StructLM-7B huggingface.co
Other API from TIGER-Lab
Total runs:
64.5K
Run Growth:
21.8K
Growth Rate:
33.87%
Total runs:
12.1K
Run Growth:
308
Growth Rate:
2.56%
Total runs:
10.6K
Run Growth:
-3.6K
Growth Rate:
-34.41%
Total runs:
5.0K
Run Growth:
1.5K
Growth Rate:
30.74%
Total runs:
1.4K
Run Growth:
120
Growth Rate:
8.64%
Total runs:
923
Run Growth:
-10.3K
Growth Rate:
-1116.36%
Total runs:
903
Run Growth:
753
Growth Rate:
83.39%
Total runs:
694
Run Growth:
0
Growth Rate:
0.00%
Total runs:
579
Run Growth:
-2.3K
Growth Rate:
-389.98%
Total runs:
498
Run Growth:
110
Growth Rate:
22.09%
Total runs:
340
Run Growth:
-759
Growth Rate:
-223.24%
Total runs:
329
Run Growth:
-192
Growth Rate:
-54.86%
Total runs:
273
Run Growth:
-474
Growth Rate:
-173.63%
Total runs:
208
Run Growth:
-232
Growth Rate:
-108.92%
Total runs:
165
Run Growth:
128
Growth Rate:
77.58%
Total runs:
156
Run Growth:
19
Growth Rate:
12.18%
Total runs:
156
Run Growth:
134
Growth Rate:
85.90%
Total runs:
153
Run Growth:
110
Growth Rate:
71.90%
Total runs:
151
Run Growth:
129
Growth Rate:
85.43%
Total runs:
121
Run Growth:
32
Growth Rate:
12.50%
Total runs:
107
Run Growth:
2.9K
Growth Rate:
59.57%
Total runs:
88
Run Growth:
79
Growth Rate:
89.77%
Total runs:
55
Run Growth:
54
Growth Rate:
100.00%
Total runs:
54
Run Growth:
50
Growth Rate:
92.59%
Total runs:
46
Run Growth:
-327
Growth Rate:
-710.87%
Total runs:
41
Run Growth:
23
Growth Rate:
52.27%
Total runs:
35
Run Growth:
13
Growth Rate:
38.24%
Total runs:
27
Run Growth:
13
Growth Rate:
50.00%
Total runs:
21
Run Growth:
-69
Growth Rate:
-328.57%
Total runs:
17
Run Growth:
0
Growth Rate:
0.00%
Total runs:
17
Run Growth:
-4
Growth Rate:
-23.53%
Total runs:
14
Run Growth:
4
Growth Rate:
30.77%
Total runs:
13
Run Growth:
0
Growth Rate:
0.00%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
13
Run Growth:
-39
Growth Rate:
-300.00%
Total runs:
13
Run Growth:
-5
Growth Rate:
-38.46%
Total runs:
12
Run Growth:
3
Growth Rate:
25.00%
Total runs:
11
Run Growth:
-26
Growth Rate:
-236.36%
Total runs:
11
Run Growth:
1
Growth Rate:
8.33%
Total runs:
10
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9
Run Growth:
-12
Growth Rate:
-133.33%
Total runs:
9
Run Growth:
-5
Growth Rate:
-50.00%
Total runs:
7
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
-3
Growth Rate:
-42.86%
Total runs:
6
Run Growth:
-11
Growth Rate:
-220.00%
Total runs:
6
Run Growth:
-7
Growth Rate:
-140.00%
Total runs:
6
Run Growth:
-2
Growth Rate:
-33.33%
Total runs:
6
Run Growth:
1
Growth Rate:
16.67%
Total runs:
6
Run Growth:
1
Growth Rate:
16.67%
Total runs:
5
Run Growth:
-23
Growth Rate:
-460.00%
Total runs:
4
Run Growth:
-5
Growth Rate:
-125.00%
Total runs:
4
Run Growth:
-1
Growth Rate:
-25.00%
Total runs:
3
Run Growth:
1
Growth Rate:
33.33%
Total runs:
2
Run Growth:
-5
Growth Rate:
-250.00%
Total runs:
2
Run Growth:
-6
Growth Rate:
-300.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
-12
Growth Rate:
-600.00%