jamescalam commited on
Commit
1a1c51b
1 Parent(s): b616ab6

added detail to model card

Browse files
Files changed (1) hide show
  1. README.md +6 -11
README.md CHANGED
@@ -5,11 +5,12 @@ tags:
5
  - feature-extraction
6
  - sentence-similarity
7
  - transformers
 
8
  ---
9
 
10
- # {MODEL_NAME}
11
 
12
- 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.
13
 
14
  <!--- Describe your model here -->
15
 
@@ -70,16 +71,10 @@ print("Sentence embeddings:")
70
  print(sentence_embeddings)
71
  ```
72
 
 
73
 
 
74
 
75
- ## Evaluation Results
76
-
77
- <!--- Describe how your model was evaluated -->
78
-
79
- For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
80
-
81
-
82
- ## Training
83
  The model was trained with the parameters:
84
 
85
  **DataLoader**:
@@ -125,4 +120,4 @@ SentenceTransformer(
125
 
126
  ## Citing & Authors
127
 
128
- <!--- Describe where people can find more information -->
 
5
  - feature-extraction
6
  - sentence-similarity
7
  - transformers
8
+ - question-answering
9
  ---
10
 
11
+ # MPNet Retriever (Discourse)
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 as a retriever model in open-domain question-answering tasks.
14
 
15
  <!--- Describe your model here -->
16
 
 
71
  print(sentence_embeddings)
72
  ```
73
 
74
+ ## Training
75
 
76
+ The model was fine-tuned on question-answer pairs scraper from several ML-focused Discourse forums \[HuggingFace, PyTorch, Streamlit, TensorFlow\].
77
 
 
 
 
 
 
 
 
 
78
  The model was trained with the parameters:
79
 
80
  **DataLoader**:
 
120
 
121
  ## Citing & Authors
122
 
123
+ Fine-tuned by [James Briggs](https://www.youtube.com/c/jamesbriggs) at [Pinecone](https://www.pinecone.io). Learn more about the [fine-tuning process here](https://www.pinecone.io/learn/retriever-models/).