yzong12138 commited on
Commit
2e4ed76
1 Parent(s): aff456e
Files changed (2) hide show
  1. README.md +7 -4
  2. definition.json +1 -1
README.md CHANGED
@@ -1,9 +1,12 @@
1
  ---
2
  library_name: xpmir
3
  ---
4
- # Runs an experiment
5
 
6
- None
 
 
 
7
 
8
  ## Using the model)
9
  The model can be loaded with [experimaestro IR](https://experimaestro-ir.readthedocs.io/en/latest/)
@@ -16,8 +19,8 @@ model = AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE")
16
 
17
  # Use this if you want to actually use the model
18
  model = AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE", as_instance=True)
19
- model.initialize(None)
20
- model.rsv("walgreens store sales average", "The average Walgreens salary ranges from approximately $15,000 per year for Customer Service Associate / Cashier to $179,900 per year for District Manager...")
21
  ```
22
 
23
  ## Results
 
1
  ---
2
  library_name: xpmir
3
  ---
4
+ # SPLADE_DistilMSE: SPLADEv2 trained with the distillated triplets
5
 
6
+ Training data from: https://github.com/sebastian-hofstaetter/neural-ranking-kd
7
+ From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models
8
+ More Effective (Thibault Formal, Carlos Lassance, Benjamin Piwowarski,
9
+ Stéphane Clinchant). 2022. https://arxiv.org/abs/2205.04733
10
 
11
  ## Using the model)
12
  The model can be loaded with [experimaestro IR](https://experimaestro-ir.readthedocs.io/en/latest/)
 
19
 
20
  # Use this if you want to actually use the model
21
  model = AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE", as_instance=True)
22
+ model.initialize()
23
+ model.rsv("walgreens store sales average", "The average Walgreens salary ranges...")
24
  ```
25
 
26
  ## Results
definition.json CHANGED
@@ -1 +1 @@
1
- [{"id": 139993107703040, "module": "xpmir.text.huggingface", "type": "TransformerVocab", "identifier": "1b34882d3bb2bdecb562df9dbc0611309178933028292b272c8d2b6121e5f6b2", "typename": "xpmir.text.huggingface.TransformerVocab", "ignored": [], "fields": {"model_id": "distilbert-base-uncased", "trainable": true, "layer": 0, "dropout": 0.0}}, {"id": 139993107702992, "module": "xpmir.neural.splade", "type": "MaxAggregation", "identifier": "6d85ac05decb4f139354ac3f79990a2afdb8ced21c8861f2dd5c720484514f48", "typename": "xpmir.neural.splade.MaxAggregation", "ignored": [], "fields": {}}, {"id": 139993107703472, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "identifier": "e54501ae9b19387204445bec69bc5a860d9e68f1e44d75733fe66b4e02418098", "typename": "xpmir.neural.splade.SpladeTextEncoder", "ignored": [], "fields": {"encoder": {"type": "python", "value": 139993107703040}, "aggregation": {"type": "python", "value": 139993107702992}, "maxlen": 200}}, {"id": 139993107704720, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "identifier": "1e5b132f4b528e408796f70295156b3ad0d6c41f669f2b43a5a1e3ab5ac7906e", "typename": "xpmir.neural.splade.SpladeTextEncoder", "ignored": [], "fields": {"encoder": {"type": "python", "value": 139993107703040}, "aggregation": {"type": "python", "value": 139993107702992}, "maxlen": 30}}, {"id": 139993107853856, "module": "xpmir.neural.dual", "type": "DotDense", "identifier": "f4bacc4feb44bae72cbe080cad5b588a32de094a89fd4524520842e342a1a48d", "fields": {"checkpoint": {"type": "path.serialized", "value": "checkpoint", "is_folder": true}, "encoder": {"type": "python", "value": 139993107703472}, "query_encoder": {"type": "python", "value": 139993107704720}}}]
 
1
+ [{"id": 139820640243856, "module": "xpmir.text.huggingface", "type": "TransformerVocab", "identifier": "1b34882d3bb2bdecb562df9dbc0611309178933028292b272c8d2b6121e5f6b2", "typename": "xpmir.text.huggingface.TransformerVocab", "ignored": [], "fields": {"model_id": "distilbert-base-uncased", "trainable": true, "layer": 0, "dropout": 0.0}}, {"id": 139820640243808, "module": "xpmir.neural.splade", "type": "MaxAggregation", "identifier": "6d85ac05decb4f139354ac3f79990a2afdb8ced21c8861f2dd5c720484514f48", "typename": "xpmir.neural.splade.MaxAggregation", "ignored": [], "fields": {}}, {"id": 139820640244288, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "identifier": "e54501ae9b19387204445bec69bc5a860d9e68f1e44d75733fe66b4e02418098", "typename": "xpmir.neural.splade.SpladeTextEncoder", "ignored": [], "fields": {"encoder": {"type": "python", "value": 139820640243856}, "aggregation": {"type": "python", "value": 139820640243808}, "maxlen": 200}}, {"id": 139820640245536, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "identifier": "1e5b132f4b528e408796f70295156b3ad0d6c41f669f2b43a5a1e3ab5ac7906e", "typename": "xpmir.neural.splade.SpladeTextEncoder", "ignored": [], "fields": {"encoder": {"type": "python", "value": 139820640243856}, "aggregation": {"type": "python", "value": 139820640243808}, "maxlen": 30}}, {"id": 139820640328608, "module": "xpmir.neural.dual", "type": "DotDense", "identifier": "f4bacc4feb44bae72cbe080cad5b588a32de094a89fd4524520842e342a1a48d", "fields": {"checkpoint": {"type": "path.serialized", "value": "checkpoint", "is_folder": true}, "encoder": {"type": "python", "value": 139820640244288}, "query_encoder": {"type": "python", "value": 139820640245536}}}]