Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
|
5 |
+
# Tiger Model Card
|
6 |
+
|
7 |
+
## Model details
|
8 |
+
|
9 |
+
Tactic-guided reasoner (Tiger) is a language model that solves *reasoning in the wild* task proposed in paper [Can LLMs Reason in the Wild with Programs](https://arxiv.org/abs/2406.13764).
|
10 |
+
It is trained by fine-tuning the LLaMA3-8B model on the [ReWild](https://huggingface.co/datasets/yuan-yang/ReWild) dataset.
|
11 |
+
|
12 |
+
**Model type:**
|
13 |
+
This repo contains the LoRA delta weights for `Tiger-Routing-8B`
|
14 |
+
|
15 |
+
We also provide the delta weights of other versions:
|
16 |
+
- [Tiger-Routing-8B](https://huggingface.co/yuan-yang/Tiger-Routing-8B/)
|
17 |
+
- [Tiger-PJ-8B](https://huggingface.co/yuan-yang/Tiger-PJ-8B)
|
18 |
+
- [Tiger-IPJ-8B](https://huggingface.co/yuan-yang/Tiger-IPJ-8B)
|
19 |
+
|
20 |
+
**License:**
|
21 |
+
Apache License 2.0
|
22 |
+
|
23 |
+
## Using the model
|
24 |
+
|
25 |
+
Check out how to use the model on our project page: https://github.com/gblackout/Reason-in-the-Wild/
|
26 |
+
|
27 |
+
|
28 |
+
**Primary intended uses:**
|
29 |
+
Tiger is intended to be used for research.
|
30 |
+
|
31 |
+
|
32 |
+
## Citation
|
33 |
+
|
34 |
+
```
|
35 |
+
@article{yang2024can,
|
36 |
+
title={Can LLMs Reason in the Wild with Programs?},
|
37 |
+
author={Yang, Yuan and Xiong, Siheng and Payani, Ali and Shareghi, Ehsan and Fekri, Faramarz},
|
38 |
+
journal={arXiv preprint arXiv:2406.13764},
|
39 |
+
year={2024}
|
40 |
+
}
|
41 |
+
```
|