pritamdeka TerriTuson commited on
Commit
dc7d9a7
1 Parent(s): 07302ce

Add BERTopic model (#4)

Browse files

- Add BERTopic model (3cc8c686cf9b8a536b5cfd4ebaba5a72872dd240)


Co-authored-by: Terri Tuson <TerriTuson@users.noreply.huggingface.co>

Files changed (3) hide show
  1. config.json +15 -23
  2. topic_embeddings.safetensors +0 -0
  3. topics.json +0 -0
config.json CHANGED
@@ -1,25 +1,17 @@
1
  {
2
- "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
3
- "architectures": [
4
- "BertModel"
 
 
 
 
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
- "layer_norm_eps": 1e-12,
14
- "max_position_embeddings": 512,
15
- "model_type": "bert",
16
- "num_attention_heads": 12,
17
- "num_hidden_layers": 12,
18
- "pad_token_id": 0,
19
- "position_embedding_type": "absolute",
20
- "torch_dtype": "float32",
21
- "transformers_version": "4.11.0",
22
- "type_vocab_size": 2,
23
- "use_cache": true,
24
- "vocab_size": 30522
25
- }
 
1
  {
2
+ "calculate_probabilities": false,
3
+ "language": "english",
4
+ "low_memory": false,
5
+ "min_topic_size": 10,
6
+ "n_gram_range": [
7
+ 1,
8
+ 1
9
  ],
10
+ "nr_topics": null,
11
+ "seed_topic_list": null,
12
+ "top_n_words": 10,
13
+ "verbose": true,
14
+ "zeroshot_min_similarity": 0.7,
15
+ "zeroshot_topic_list": null,
16
+ "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
17
+ }
 
 
 
 
 
 
 
 
 
 
 
 
topic_embeddings.safetensors ADDED
Binary file (131 kB). View file
 
topics.json ADDED
The diff for this file is too large to render. See raw diff