jordiclive
commited on
Commit
•
e1f3331
1
Parent(s):
be4c3ae
Update README.md
Browse files
README.md
CHANGED
@@ -96,4 +96,17 @@ The following hyperparameters were used during training:
|
|
96 |
- Transformers 4.24.0
|
97 |
- Pytorch 1.9.1+cu111
|
98 |
- Deepspeed 0.7.4
|
99 |
-
- Pytorch-lightning 1.8.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
- Transformers 4.24.0
|
97 |
- Pytorch 1.9.1+cu111
|
98 |
- Deepspeed 0.7.4
|
99 |
+
- Pytorch-lightning 1.8.1
|
100 |
+
|
101 |
+
|
102 |
+
### Citation
|
103 |
+
```
|
104 |
+
@misc{jordiclive_flan_t5_3b_summarizer_2023,
|
105 |
+
title={{Multi-purpose Summarizer (Fine-tuned google/flan-t5-xl on several Summarization datasets)}},
|
106 |
+
author={{Jordan Clive}},
|
107 |
+
howpublished={\url{https://huggingface.co/jordiclive/flan-t5-3b-summarizer}},
|
108 |
+
year={2023},
|
109 |
+
note={Apache 2.0 and BSD-3-Clause License. Fine-tuned on various summarization datasets including xsum, wikihow, cnn_dailymail/3.0.0, samsum, scitldr/AIC, billsum, TLDR. Designed for academic and general usage with control over summary type by varying the instruction prepended to the source document.},
|
110 |
+
url={https://huggingface.co/jordiclive/flan-t5-3b-summarizer},
|
111 |
+
}
|
112 |
+
```
|