jzfeng commited on
Commit
eff38f4
1 Parent(s): 7c1cac9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -1
README.md CHANGED
@@ -8,4 +8,27 @@ pipeline_tag: question-answering
8
  tags:
9
  - logical reasoning
10
  - reasoning
11
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  tags:
9
  - logical reasoning
10
  - reasoning
11
+ ---
12
+
13
+ ## Model Details
14
+
15
+ These are the trained models for **LoGiPT** from NAACL'24 paper: *"Language Models can be Deductive Solvers"*.
16
+
17
+ - LoGiPT-[A]-[B]: The specific model version of LoGiPT
18
+ - [A]: The backbone model, which can be 'vicuna-13b-v1.5-16k', 'CodeLlama-13b-hf' or 'CodeLlama-13b-Instruct-hf'.
19
+ - [B]: The training data, which can be 'proofwriter' or 'prontoqa'.
20
+
21
+ All models are organised in Vicuna-style and trained by [FastChat-0.2.30](https://github.com/lm-sys/FastChat).
22
+
23
+ All training examples are organised in Json-format and Vicuna-style in [jzfeng/LoGiPT-data](https://huggingface.co/datasets/jzfeng/LoGiPT-data).
24
+
25
+ ### If you find these models helpful, please cite our NAACL'24 paper: (or Arxiv version: https://arxiv.org/abs/2311.06158)
26
+ ```shell
27
+ @inproceedings{feng2024language,
28
+ title={Language Models can be Deductive Solvers},
29
+ author={Feng, Jiazhan and Xu, Ruochen and Hao, Junheng and Sharma, Hiteshi and Shen, Yelong and Zhao, Dongyan and Chen, Weizhu},
30
+ booktitle={Findings of the Association for Computational Linguistics: NAACL 2024},
31
+ pages={4026--4042},
32
+ year={2024}
33
+ }
34
+ ```