Instructions to use nhmnhat1997/condenser-phobert-biencoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nhmnhat1997/condenser-phobert-biencoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nhmnhat1997/condenser-phobert-biencoder") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use nhmnhat1997/condenser-phobert-biencoder with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nhmnhat1997/condenser-phobert-biencoder") model = AutoModel.from_pretrained("nhmnhat1997/condenser-phobert-biencoder") - Notebooks
- Google Colab
- Kaggle
Commit ·
c64444c
1
Parent(s): 7a4b7bd
Upload config.json
Browse files- config.json +28 -6
config.json
CHANGED
|
@@ -1,7 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/ubuntu/nhatnhm2/deepImpact/Condenser-pho-bert/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 258,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.30.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 64001
|
| 29 |
+
}
|