Brendan commited on
Commit
2a9a131
1 Parent(s): ff934cd

update Model Card

Browse files
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -8,7 +8,11 @@ tags:
8
 
9
  ---
10
 
11
- # {MODEL_NAME}
 
 
 
 
12
 
13
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
 
@@ -28,7 +32,7 @@ Then you can use the model like this:
28
  from sentence_transformers import SentenceTransformer
29
  sentences = ["This is an example sentence", "Each sentence is converted"]
30
 
31
- model = SentenceTransformer('{MODEL_NAME}')
32
  embeddings = model.encode(sentences)
33
  print(embeddings)
34
  ```
@@ -54,8 +58,8 @@ def mean_pooling(model_output, attention_mask):
54
  sentences = ['This is an example sentence', 'Each sentence is converted']
55
 
56
  # Load model from HuggingFace Hub
57
- tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
58
- model = AutoModel.from_pretrained('{MODEL_NAME}')
59
 
60
  # Tokenize sentences
61
  encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -77,7 +81,7 @@ print(sentence_embeddings)
77
 
78
  <!--- Describe how your model was evaluated -->
79
 
80
- For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
81
 
82
 
83
  ## Training
 
8
 
9
  ---
10
 
11
+ # Brendan/refpydst-1p-icdst-split-v1
12
+
13
+ This model was initialized with `sentence-transformers/all-mpnet-base-v2` and then fine-tuned using a 1% few-shot split of the MultiWOZ dataset and a supervised contrastive loss. It is fine-tuned to be used as an in-context example retriever using this few-shot training set, which is provided in the linked repository. More details available [in the repo](https://github.com/jlab-nlp/RefPyDST) and paper linked within. To cite this model, please consult the citation in the [linked GithHub repository README](https://github.com/jlab-nlp/RefPyDST).
14
+
15
+ The remainder of this README is automatically generated from `sentence_transformers` and is accurate, though this model is not intended as a general purpose sentence-encoder: it is expecting in-context examples from MultiWOZ to be formatted in a particular way, see the linked repo for details.
16
 
17
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
18
 
 
32
  from sentence_transformers import SentenceTransformer
33
  sentences = ["This is an example sentence", "Each sentence is converted"]
34
 
35
+ model = SentenceTransformer('Brendan/refpydst-1p-icdst-split-v1')
36
  embeddings = model.encode(sentences)
37
  print(embeddings)
38
  ```
 
58
  sentences = ['This is an example sentence', 'Each sentence is converted']
59
 
60
  # Load model from HuggingFace Hub
61
+ tokenizer = AutoTokenizer.from_pretrained('Brendan/refpydst-1p-icdst-split-v1')
62
+ model = AutoModel.from_pretrained('Brendan/refpydst-1p-icdst-split-v1')
63
 
64
  # Tokenize sentences
65
  encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
 
81
 
82
  <!--- Describe how your model was evaluated -->
83
 
84
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=Brendan/refpydst-1p-icdst-split-v1)
85
 
86
 
87
  ## Training