Update README.md
Browse files
README.md
CHANGED
@@ -38,9 +38,9 @@ model-index:
|
|
38 |
name: Solution Exact Match
|
39 |
---
|
40 |
|
41 |
-
# Phi-3 Mini 4K Verbalized Rebus Solver 🇮🇹
|
42 |
|
43 |
-
This model is a parameter-efficient fine-tuned version of Phi-3 Mini 4K trained for verbalized rebus solving in Italian, as part of the [release](https://huggingface.co/collections/gsarti/verbalized-rebus-clic-it-2024-66ab8f11cb04e68bdf4fb028) for our paper [Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses](
|
44 |
|
45 |
The model was trained in 4-bit precision for 5070 steps on the verbalized subset of the [EurekaRebus](https://huggingface.co/datasets/gsarti/eureka-rebus) using QLora via [Unsloth](https://github.com/unslothai/unsloth) and [TRL](https://github.com/huggingface/trl). This repository contains PEFT-compatible adapters saved throughout training. Use the `revision=<GIT_HASH>` parameter in `from_pretrained` to load mid-training adapter checkpoints.
|
46 |
|
@@ -127,7 +127,15 @@ For problems or updates on this model, please contact [[email protected]
|
|
127 |
If you use this model in your work, please cite our paper as follows:
|
128 |
|
129 |
```bibtex
|
130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
131 |
```
|
132 |
|
133 |
## Acknowledgements
|
|
|
38 |
name: Solution Exact Match
|
39 |
---
|
40 |
|
41 |
+
# Phi-3 Mini 4K Verbalized Rebus Solver - PEFT Adapters 🇮🇹
|
42 |
|
43 |
+
This model is a parameter-efficient fine-tuned version of Phi-3 Mini 4K trained for verbalized rebus solving in Italian, as part of the [release](https://huggingface.co/collections/gsarti/verbalized-rebus-clic-it-2024-66ab8f11cb04e68bdf4fb028) for our paper [Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses](https://arxiv.org/abs/2408.00584). The task of verbalized rebus solving consists of converting an encrypted sequence of letters and crossword definitions into a solution phrase matching the word lengths specified in the solution key. An example is provided below.
|
44 |
|
45 |
The model was trained in 4-bit precision for 5070 steps on the verbalized subset of the [EurekaRebus](https://huggingface.co/datasets/gsarti/eureka-rebus) using QLora via [Unsloth](https://github.com/unslothai/unsloth) and [TRL](https://github.com/huggingface/trl). This repository contains PEFT-compatible adapters saved throughout training. Use the `revision=<GIT_HASH>` parameter in `from_pretrained` to load mid-training adapter checkpoints.
|
46 |
|
|
|
127 |
If you use this model in your work, please cite our paper as follows:
|
128 |
|
129 |
```bibtex
|
130 |
+
@article{sarti-etal-2024-rebus,
|
131 |
+
title = "Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses",
|
132 |
+
author = "Sarti, Gabriele and Caselli, Tommaso and Nissim, Malvina and Bisazza, Arianna",
|
133 |
+
journal = "ArXiv",
|
134 |
+
month = jul,
|
135 |
+
year = "2024",
|
136 |
+
volume = {abs/2408.00584},
|
137 |
+
url = {https://arxiv.org/abs/2408.00584},
|
138 |
+
}
|
139 |
```
|
140 |
|
141 |
## Acknowledgements
|