gsarti commited on
Commit
8585882
•
1 Parent(s): 5ca8984

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -2
README.md CHANGED
@@ -40,7 +40,7 @@ model-index:
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](TBD). 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 version has merged adapter weights in half precision, enabling out-of-the-box for usage with the `transformers` library.
46
 
@@ -133,7 +133,15 @@ For problems or updates on this model, please contact [gabriele.sarti996@gmail.c
133
  If you use this model in your work, please cite our paper as follows:
134
 
135
  ```bibtex
136
- TBD
 
 
 
 
 
 
 
 
137
  ```
138
 
139
  ## Acknowledgements
 
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](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 version has merged adapter weights in half precision, enabling out-of-the-box for usage with the `transformers` library.
46
 
 
133
  If you use this model in your work, please cite our paper as follows:
134
 
135
  ```bibtex
136
+ @article{sarti-etal-2024-rebus,
137
+ title = "Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses",
138
+ author = "Sarti, Gabriele and Caselli, Tommaso and Nissim, Malvina and Bisazza, Arianna",
139
+ journal = "ArXiv",
140
+ month = jul,
141
+ year = "2024",
142
+ volume = {abs/2408.00584},
143
+ url = {https://arxiv.org/abs/2408.00584},
144
+ }
145
  ```
146
 
147
  ## Acknowledgements