rasyosef commited on
Commit
b9916e1
·
verified ·
1 Parent(s): 19b91e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -7
README.md CHANGED
@@ -7,6 +7,8 @@ tags:
7
  - retrieval
8
  - search
9
  - sparse
 
 
10
  ---
11
 
12
  # Splade-Index
@@ -32,20 +34,17 @@ pip install huggingface_hub
32
  You can use the following code to load this SPLADE index from Hugging Face hub:
33
 
34
  ```python
35
- import os
36
  from sentence_transformers import SparseEncoder
37
  from splade_index import SPLADE
38
 
39
  # Download the SPLADE model that was used to create the index from the HuggingFace Hub
40
- model_id = "the-splade-model-id" # Enter the splade model id
41
  model = SparseEncoder(model_id)
42
 
43
- # Set your huggingface token if repo is private
44
- token = os.environ["HF_TOKEN"]
45
  repo_id = "rasyosef/natural_questions_3m_splade_index"
46
 
47
  # Load a SPLADE index from the Hugging Face model hub
48
- retriever = SPLADE.load_from_hub(repo_id, model=model, token=token)
49
  ```
50
 
51
  ## Stats
@@ -56,5 +55,4 @@ This dataset was created using the following data:
56
  | --- | --- |
57
  | Number of documents | 2681468 |
58
  | Number of tokens | 464573223 |
59
- | Average tokens per document | 173.25 |
60
-
 
7
  - retrieval
8
  - search
9
  - sparse
10
+ datasets:
11
+ - mteb/nq
12
  ---
13
 
14
  # Splade-Index
 
34
  You can use the following code to load this SPLADE index from Hugging Face hub:
35
 
36
  ```python
 
37
  from sentence_transformers import SparseEncoder
38
  from splade_index import SPLADE
39
 
40
  # Download the SPLADE model that was used to create the index from the HuggingFace Hub
41
+ model_id = "rasyosef/splade-tiny" # The splade model id
42
  model = SparseEncoder(model_id)
43
 
 
 
44
  repo_id = "rasyosef/natural_questions_3m_splade_index"
45
 
46
  # Load a SPLADE index from the Hugging Face model hub
47
+ retriever = SPLADE.load_from_hub(repo_id, model=model)
48
  ```
49
 
50
  ## Stats
 
55
  | --- | --- |
56
  | Number of documents | 2681468 |
57
  | Number of tokens | 464573223 |
58
+ | Average tokens per document | 173.25 |