Update README.md
Browse files
README.md
CHANGED
@@ -3,10 +3,8 @@ language:
|
|
3 |
- en
|
4 |
|
5 |
tags:
|
6 |
-
- token-classification
|
7 |
- text-classification
|
8 |
-
-
|
9 |
-
- text2text-generation
|
10 |
- text-generation
|
11 |
|
12 |
datasets:
|
@@ -15,9 +13,12 @@ datasets:
|
|
15 |
|
16 |
---
|
17 |
|
18 |
-
# SciFive Pubmed+PMC Large
|
19 |
|
20 |
## Introduction
|
|
|
|
|
|
|
21 |
Paper: [SciFive: a text-to-text transformer model for biomedical literature](https://arxiv.org/abs/2106.03598)
|
22 |
|
23 |
Authors: _Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet_
|
@@ -31,7 +32,7 @@ tokenizer = AutoTokenizer.from_pretrained("razent/SciFive-large-Pubmed_PMC")
|
|
31 |
model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-large-Pubmed_PMC")
|
32 |
|
33 |
sentence = "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor ."
|
34 |
-
text = "
|
35 |
|
36 |
encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
|
37 |
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")
|
|
|
3 |
- en
|
4 |
|
5 |
tags:
|
|
|
6 |
- text-classification
|
7 |
+
- mednli
|
|
|
8 |
- text-generation
|
9 |
|
10 |
datasets:
|
|
|
13 |
|
14 |
---
|
15 |
|
16 |
+
# SciFive Pubmed+PMC Large on MedNLI
|
17 |
|
18 |
## Introduction
|
19 |
+
|
20 |
+
Finetuned SciFive Pubmed+PMC Large model achieved state-of-the-art results on [MedNLI (Medical Natural Language Inference)](https://paperswithcode.com/sota/natural-language-inference-on-mednli)
|
21 |
+
|
22 |
Paper: [SciFive: a text-to-text transformer model for biomedical literature](https://arxiv.org/abs/2106.03598)
|
23 |
|
24 |
Authors: _Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet_
|
|
|
32 |
model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-large-Pubmed_PMC")
|
33 |
|
34 |
sentence = "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor ."
|
35 |
+
text = "mednli: " + sentence + " </s>"
|
36 |
|
37 |
encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
|
38 |
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")
|