Upload RobertaForSequenceClassification
Browse files- README.md +4 -12
- config.json +3 -3
- model.safetensors +2 -2
README.md
CHANGED
@@ -4,19 +4,12 @@ language:
|
|
4 |
license: mit
|
5 |
datasets:
|
6 |
- cardiffnlp/super_tweeteval
|
7 |
-
pipeline_tag:
|
8 |
-
inference:
|
9 |
-
parameters:
|
10 |
-
function_to_apply: none
|
11 |
-
widget:
|
12 |
-
- text: >-
|
13 |
-
Looooooool what is this story #TalksWithAsh </s> For someone who keeps
|
14 |
-
saying long story short, the story is quite long iyah #TalksWithAsh
|
15 |
---
|
16 |
# cardiffnlp/twitter-roberta-large-similarity-latest
|
17 |
|
18 |
This is a RoBERTa-large model trained on 154M tweets until the end of December 2022 and finetuned for tweet similarity (regression on two texts) on the _TweetSIM_ dataset of [SuperTweetEval](https://huggingface.co/datasets/cardiffnlp/super_tweeteval).
|
19 |
-
The original Twitter-
|
20 |
|
21 |
## Example
|
22 |
```python
|
@@ -32,9 +25,8 @@ text_2 = 'For someone who keeps saying long story short, the story is quite long
|
|
32 |
|
33 |
text_input = f"{text_1} </s> {text_2}"
|
34 |
|
35 |
-
|
36 |
-
|
37 |
-
>> [{'label': 'LABEL_0', 'score': 2.956475019454956}]
|
38 |
```
|
39 |
|
40 |
|
|
|
4 |
license: mit
|
5 |
datasets:
|
6 |
- cardiffnlp/super_tweeteval
|
7 |
+
pipeline_tag: sentence-similarity
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
# cardiffnlp/twitter-roberta-large-similarity-latest
|
10 |
|
11 |
This is a RoBERTa-large model trained on 154M tweets until the end of December 2022 and finetuned for tweet similarity (regression on two texts) on the _TweetSIM_ dataset of [SuperTweetEval](https://huggingface.co/datasets/cardiffnlp/super_tweeteval).
|
12 |
+
The original Twitter-based RoBERTa model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-large-2022-154m).
|
13 |
|
14 |
## Example
|
15 |
```python
|
|
|
25 |
|
26 |
text_input = f"{text_1} </s> {text_2}"
|
27 |
|
28 |
+
model(**tokenizer(text_input, return_tensors="pt")).logits
|
29 |
+
>>tensor([[2.9565]])
|
|
|
30 |
```
|
31 |
|
32 |
|
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
@@ -27,7 +27,7 @@
|
|
27 |
"position_embedding_type": "absolute",
|
28 |
"problem_type": "regression",
|
29 |
"torch_dtype": "float32",
|
30 |
-
"transformers_version": "4.
|
31 |
"type_vocab_size": 1,
|
32 |
"use_cache": true,
|
33 |
"vocab_size": 50265
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "best_models/troberta-large-tweet-similarity/best_model",
|
3 |
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
27 |
"position_embedding_type": "absolute",
|
28 |
"problem_type": "regression",
|
29 |
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.38.2",
|
31 |
"type_vocab_size": 1,
|
32 |
"use_cache": true,
|
33 |
"vocab_size": 50265
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:639af2e2b0f8cf113f102236523936b14bce097c00dec7ed92aba0a39a4b2174
|
3 |
+
size 1421491316
|