Add model

README.md

@@ -2,29 +2,34 @@
 library_name: xpmir
 ---
 # SPLADE_DistilMSE: SPLADEv2 trained with the distillated triplets
-
 Training data from: https://github.com/sebastian-hofstaetter/neural-ranking-kd
 
 From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models
 More Effective (Thibault Formal, Carlos Lassance, Benjamin Piwowarski,
 Stéphane Clinchant). 2022. https://arxiv.org/abs/2205.04733
 
-## Using the model)
-The model can be loaded with [experimaestro IR](https://experimaestro-ir.readthedocs.io/en/latest/)
 
-```py
-from xpmir.models import AutoModel
 
-# Model that can be re-used in experiments
-model = AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE")
 
-# Use this if you want to actually use the model
-model = AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE", as_instance=True)
-model.initialize()
-model.rsv("walgreens store sales average", "The average Walgreens salary ranges...")
+
+## Using the model
+The model can be loaded with [experimaestro
+IR](https://experimaestro-ir.readthedocs.io/en/latest/)
+
+```py from xpmir.models import AutoModel
+
+# Model that can be re-used in experiments model =
+AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE")
+
+# Use this if you want to actually use the model model =
+AutoModel.load_from_hf_hub("xpmir/SPLADE_DistilMSE", as_instance=True)
+model.initialize() model.rsv("walgreens store sales average", "The average
+Walgreens salary ranges...")
 ```
 
+
 ## Results
+
 | Dataset  | AP | P@20 | RR | RR@10 | nDCG | nDCG@10 | nDCG@20  |
 |----| ---|------|------|------|------|------|------|
 | trec2019 | 0.5102 | 0.7360 | 0.9612 | 0.9612 | 0.7407 | 0.7300 | 0.7097 |

definition.json

@@ -1 +1 @@
-[{"id": 140693356415392, "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": 140693356415344, "module": "xpmir.neural.splade", "type": "MaxAggregation", "identifier": "6d85ac05decb4f139354ac3f79990a2afdb8ced21c8861f2dd5c720484514f48", "typename": "xpmir.neural.splade.MaxAggregation", "ignored": [], "fields": {}}, {"id": 140693356415824, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "identifier": "e54501ae9b19387204445bec69bc5a860d9e68f1e44d75733fe66b4e02418098", "typename": "xpmir.neural.splade.SpladeTextEncoder", "ignored": [], "fields": {"encoder": {"type": "python", "value": 140693356415392}, "aggregation": {"type": "python", "value": 140693356415344}, "maxlen": 200}}, {"id": 140693356417072, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "identifier": "1e5b132f4b528e408796f70295156b3ad0d6c41f669f2b43a5a1e3ab5ac7906e", "typename": "xpmir.neural.splade.SpladeTextEncoder", "ignored": [], "fields": {"encoder": {"type": "python", "value": 140693356415392}, "aggregation": {"type": "python", "value": 140693356415344}, "maxlen": 30}}, {"id": 140693356500144, "module": "xpmir.neural.dual", "type": "DotDense", "identifier": "f4bacc4feb44bae72cbe080cad5b588a32de094a89fd4524520842e342a1a48d", "fields": {"checkpoint": {"type": "path.serialized", "value": "checkpoint", "is_folder": true}, "encoder": {"type": "python", "value": 140693356415824}, "query_encoder": {"type": "python", "value": 140693356417072}}}]
+[{"id": 140703274169536, "module": "xpmir.text.huggingface", "type": "TransformerTokensEncoder", "typename": "xpmir.text.huggingface.TransformerTokensEncoder", "identifier": "d26c7c4d00bb2002f07f80036294ed81355c1256fde3758c6ab9451c7fc06c2c", "fields": {"model_id": "distilbert-base-uncased", "trainable": true, "layer": 0, "dropout": 0.0}}, {"id": 140703274169104, "module": "xpmir.neural.splade", "type": "MaxAggregation", "typename": "xpmir.neural.splade.MaxAggregation", "identifier": "6d85ac05decb4f139354ac3f79990a2afdb8ced21c8861f2dd5c720484514f48", "fields": {}}, {"id": 140703274169824, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "typename": "xpmir.neural.splade.SpladeTextEncoder", "identifier": "9f455ba2eb9c3dc5ce40d4f0620b24a8d086b1a35449380af6cf625a69f2efeb", "fields": {"encoder": {"type": "python", "value": 140703274169536}, "aggregation": {"type": "python", "value": 140703274169104}, "maxlen": 200}}, {"id": 140703274171744, "module": "xpmir.neural.splade", "type": "SpladeTextEncoder", "typename": "xpmir.neural.splade.SpladeTextEncoder", "identifier": "af02fa8dcdc136f3c02eeb124fe524302c85d736deeaa6d04b3acc215d1593ac", "fields": {"encoder": {"type": "python", "value": 140703274169536}, "aggregation": {"type": "python", "value": 140703274169104}, "maxlen": 30}}, {"id": 140703274334768, "module": "xpmir.neural.dual", "type": "DotDense", "typename": "xpmir.neural.dual.DotDense", "identifier": "d4e16bd0471b8b48c996614c52a927c911296acf20fca61b75b431499cf47b47", "fields": {"checkpoint": {"type": "path.serialized", "value": "checkpoint", "is_folder": true}, "encoder": {"type": "python", "value": 140703274169824}, "query_encoder": {"type": "python", "value": 140703274171744}}}]

runs/splade_max-bert_hard_negative-RR@10/1675450725.7928324/events.out.tfevents.1675450725.aerosmith.82538.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2225cd840fac5f182c7fd08e6eb45a0f360f354749c539da84dfd2fe1f6630
+size 584

runs/splade_max-bert_hard_negative-RR@10/events.out.tfevents.1675334263.aerosmith.82538.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b23977a9a69a7fe684b26eb694e62ff6e486d9bb3119b253353538f9bb30092
+size 2230970