Cache scibert locally and load it.

app.py

@@ -111,7 +111,8 @@ def read_kp_encoder(in_path):
     :return:
     """
     if 'kp_enc_model' not in st.session_state:
-        word_embedding_model = models.Transformer('allenai/scibert_scivocab_uncased', max_seq_length=512)
+        word_embedding_model = models.Transformer(os.path.join(in_path, 'models', 'scibert_scivocab_uncased'),
+                                                  max_seq_length=512)
         trained_model_fname = os.path.join(in_path, 'models', 'kp_encoder_cur_best.pt')
         if torch.cuda.is_available():
             saved_model = torch.load(trained_model_fname)

data/models/scibert_scivocab_uncased/README.md

@@ -0,0 +1,29 @@
+---
+language: en
+---
+# SciBERT
+
+This is the pretrained model presented in [SciBERT: A Pretrained Language Model for Scientific Text](https://www.aclweb.org/anthology/D19-1371/), which is a BERT model trained on scientific text.
+
+The training corpus was papers taken from [Semantic Scholar](https://www.semanticscholar.org). Corpus size is 1.14M papers, 3.1B tokens. We use the full text of the papers in training, not just abstracts.
+
+SciBERT has its own wordpiece vocabulary (scivocab) that's built to best match the training corpus. We trained cased and uncased versions. 
+
+Available models include:
+* `scibert_scivocab_cased`
+* `scibert_scivocab_uncased`
+
+
+The original repo can be found [here](https://github.com/allenai/scibert).
+
+If using these models, please cite the following paper:
+```
+@inproceedings{beltagy-etal-2019-scibert,
+    title = "SciBERT: A Pretrained Language Model for Scientific Text",
+    author = "Beltagy, Iz  and Lo, Kyle  and Cohan, Arman",
+    booktitle = "EMNLP",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://www.aclweb.org/anthology/D19-1371"
+}
+```

data/models/scibert_scivocab_uncased/config.json

@@ -0,0 +1,16 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 31090
+}

data/models/scibert_scivocab_uncased/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e492944d88ac97dee6baa547671d3c526a3d067676883efb058311f4e5882e1a
+size 442221694