Arpan Chatterjee commited on
Commit
840725d
1 Parent(s): 96c87c0

Added data pickle file and trained model

Browse files
app.py CHANGED
@@ -1,4 +1,15 @@
1
  import streamlit as st
 
2
 
 
 
 
 
 
 
 
 
3
  x = st.slider('Select a value')
4
- st.write(x, 'squared is', x * x)
 
 
 
1
  import streamlit as st
2
+ import pandas as pd
3
 
4
+ #_METADATA_PATH = "https://huggingface.co/datasets/HUPD/hupd/resolve/main/hupd_metadata_2022-02-22.feather"
5
+ # Read the feather
6
+ #df = pd.read_feather(_METADATA_PATH)
7
+ df = pd.read_pickle("my_dataframe.pkl")
8
+ print(df.head(5))
9
+ print(df["abstract"][4])
10
+
11
+ '''
12
  x = st.slider('Select a value')
13
+ st.write(x, 'squared is', x * x)
14
+
15
+ '''
model-patent-score/model-patent-score/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "problem_type": "single_label_classification",
19
+ "qa_dropout": 0.1,
20
+ "seq_classif_dropout": 0.2,
21
+ "sinusoidal_pos_embds": false,
22
+ "tie_weights_": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.28.1",
25
+ "vocab_size": 28996
26
+ }
model-patent-score/model-patent-score/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21758bb62ef1248589c691c48d4ae73e2dc98ccd9e5c6735021b242936722bc1
3
+ size 263167661
model-patent-score/model-patent-score/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
model-patent-score/model-patent-score/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
model-patent-score/model-patent-score/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
model-patent-score/model-patent-score/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e14162615aa828c187927cf72413807a11124356dbda0c7f3010377b47f1ea
3
+ size 3579
model-patent-score/model-patent-score/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
my_dataframe.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed0fa496ba5d59ef30ee911d1f80221c939f9a0d126e3f6ab185f4d74898c68
3
+ size 59157061