arthurangelici
commited on
Commit
•
bee308f
1
Parent(s):
95a722c
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
|
2 |
Usage
|
3 |
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- samsum
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
+
model-index:
|
10 |
+
- name: flan-t5-xxl-lora-samsum
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: samsum
|
17 |
+
type: samsum
|
18 |
+
config: samsum
|
19 |
+
split: train
|
20 |
+
args: samsum
|
21 |
+
metrics:
|
22 |
+
- name: Rouge1
|
23 |
+
type: rouge
|
24 |
+
value: 51.2543
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# flan-t5-base-samsum
|
31 |
+
|
32 |
+
This model is a fine-tuned (with Lora and peft) version of [google/flan-t5-xxl](https://huggingface.co/google/flan-t5-xxl) on the samsum dataset.
|
33 |
+
|
34 |
+
### Framework versions
|
35 |
+
|
36 |
+
- Transformers 4.25.1
|
37 |
+
- Pytorch 1.12.1+cu113
|
38 |
+
- Datasets 2.8.0
|
39 |
+
- Tokenizers 0.12.1
|
40 |
|
41 |
Usage
|
42 |
|