Update README.md
Browse files
README.md
CHANGED
@@ -63,7 +63,7 @@ Florian Leurer compared Phoenix to other LLMs. Check it out here:
|
|
63 |
### Model Sources
|
64 |
|
65 |
- **Repository:** -
|
66 |
-
- **Paper:** https://arxiv.org/abs/2401.10580
|
67 |
- **Demo:** -
|
68 |
|
69 |
## Training Details
|
@@ -164,6 +164,18 @@ The following hyperparameters were used during training:
|
|
164 |
- lr_scheduler_warmup_ratio: 0.1
|
165 |
- num_epochs: 1
|
166 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
167 |
|
168 |
### Framework versions
|
169 |
|
|
|
63 |
### Model Sources
|
64 |
|
65 |
- **Repository:** -
|
66 |
+
- **Paper:** [`PHOENIX: Open-Source Language Adaption for Direct Preference Optimization`](https://arxiv.org/abs/2401.10580)
|
67 |
- **Demo:** -
|
68 |
|
69 |
## Training Details
|
|
|
164 |
- lr_scheduler_warmup_ratio: 0.1
|
165 |
- num_epochs: 1
|
166 |
|
167 |
+
### Citation
|
168 |
+
```
|
169 |
+
@misc{uhlig2024phoenix,
|
170 |
+
title={PHOENIX: Open-Source Language Adaption for Direct Preference Optimization},
|
171 |
+
author={Matthias Uhlig and Sigurd Schacht and Sudarshan Kamath Barkur},
|
172 |
+
year={2024},
|
173 |
+
eprint={2401.10580},
|
174 |
+
archivePrefix={arXiv},
|
175 |
+
primaryClass={cs.CL}
|
176 |
+
}
|
177 |
+
```
|
178 |
+
|
179 |
|
180 |
### Framework versions
|
181 |
|