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 the GGUF exported checkpoint of the model in `Q8_0` format, and the `Modelfile` for usage with [Ollama](https://ollama.com/) (see below).
|
46 |
|
@@ -67,7 +67,15 @@ For problems or updates on this model, please contact [[email protected]
|
|
67 |
If you use this model in your work, please cite our paper as follows:
|
68 |
|
69 |
```bibtex
|
70 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
```
|
72 |
|
73 |
## Acknowledgements
|
|
|
38 |
name: Solution Exact Match
|
39 |
---
|
40 |
|
41 |
+
# Phi-3 Mini 4K Verbalized Rebus Solver - GGUF Q8_0 🇮🇹
|
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 the GGUF exported checkpoint of the model in `Q8_0` format, and the `Modelfile` for usage with [Ollama](https://ollama.com/) (see below).
|
46 |
|
|
|
67 |
If you use this model in your work, please cite our paper as follows:
|
68 |
|
69 |
```bibtex
|
70 |
+
@article{sarti-etal-2024-rebus,
|
71 |
+
title = "Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses",
|
72 |
+
author = "Sarti, Gabriele and Caselli, Tommaso and Nissim, Malvina and Bisazza, Arianna",
|
73 |
+
journal = "ArXiv",
|
74 |
+
month = jul,
|
75 |
+
year = "2024",
|
76 |
+
volume = {abs/2408.00584},
|
77 |
+
url = {https://arxiv.org/abs/2408.00584},
|
78 |
+
}
|
79 |
```
|
80 |
|
81 |
## Acknowledgements
|