Add SciFive MedNLI models

README.md

@@ -0,0 +1,48 @@
+---
+language: 
+  - en
+
+tags:
+- token-classification
+- text-classification
+- question-answering
+- text2text-generation
+- text-generation
+
+datasets:
+- pubmed
+- pmc/open_access
+
+---
+
+# SciFive Pubmed+PMC Large
+
+## Introduction
+Paper: [SciFive: a text-to-text transformer model for biomedical literature](https://arxiv.org/abs/2106.03598)
+
+Authors: _Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet_
+
+## How to use
+For more details, do check out [our Github repo](https://github.com/justinphan3110/SciFive). 
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+​
+tokenizer = AutoTokenizer.from_pretrained("razent/SciFive-large-Pubmed_PMC")  
+model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-large-Pubmed_PMC")
+​
+sentence = "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor ."
+text =  "ncbi_ner: " + sentence + " </s>"
+
+encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
+input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")
+
+outputs = model.generate(
+    input_ids=input_ids, attention_mask=attention_masks,
+    max_length=256,
+    early_stopping=True
+)
+
+for output in outputs:
+    line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
+    print(line)
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 1024,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "nli": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "mednli: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a348b5c18206449576ce89e97932fa62777db440dd1194407e90fe85ca78eae
+size 2950897543

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ed08a95f635e6d2de102d21db1b8c831782659dd8ceec55c655044ae302780
+size 2951711704