razent commited on
Commit
0339a81
1 Parent(s): 10e8e91

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -3,10 +3,8 @@ language:
3
  - en
4
 
5
  tags:
6
- - token-classification
7
  - text-classification
8
- - question-answering
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 = "ncbi_ner: " + sentence + " </s>"
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")