metadata
base_model: BeastyZ/e5-R-mistral-7b
datasets:
- BeastyZ/E5-R
language:
- en
library_name: transformers
license: apache-2.0
tags:
- mteb
- llama-cpp
- gguf-my-repo
model-index:
- name: e5-R-mistral-7b
results:
- task:
type: Retrieval
dataset:
name: MTEB ArguAna
type: mteb/arguana
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 33.57
- type: map_at_10
value: 49.952000000000005
- type: map_at_100
value: 50.673
- type: map_at_1000
value: 50.674
- type: map_at_3
value: 44.915
- type: map_at_5
value: 47.876999999999995
- type: mrr_at_1
value: 34.211000000000006
- type: mrr_at_10
value: 50.19
- type: mrr_at_100
value: 50.905
- type: mrr_at_1000
value: 50.906
- type: mrr_at_3
value: 45.128
- type: mrr_at_5
value: 48.097
- type: ndcg_at_1
value: 33.57
- type: ndcg_at_10
value: 58.994
- type: ndcg_at_100
value: 61.806000000000004
- type: ndcg_at_1000
value: 61.824999999999996
- type: ndcg_at_3
value: 48.681000000000004
- type: ndcg_at_5
value: 54.001
- type: precision_at_1
value: 33.57
- type: precision_at_10
value: 8.784
- type: precision_at_100
value: 0.9950000000000001
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 19.867
- type: precision_at_5
value: 14.495
- type: recall_at_1
value: 33.57
- type: recall_at_10
value: 87.83800000000001
- type: recall_at_100
value: 99.502
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 59.602
- type: recall_at_5
value: 72.475
- type: main_score
value: 58.994
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackRetrieval
type: mteb/cqadupstack
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.75
- type: map_at_10
value: 34.025
- type: map_at_100
value: 35.126000000000005
- type: map_at_1000
value: 35.219
- type: map_at_3
value: 31.607000000000003
- type: map_at_5
value: 32.962
- type: mrr_at_1
value: 27.357
- type: mrr_at_10
value: 36.370999999999995
- type: mrr_at_100
value: 37.364000000000004
- type: mrr_at_1000
value: 37.423
- type: mrr_at_3
value: 34.288000000000004
- type: mrr_at_5
value: 35.434
- type: ndcg_at_1
value: 27.357
- type: ndcg_at_10
value: 46.593999999999994
- type: ndcg_at_100
value: 44.317
- type: ndcg_at_1000
value: 46.475
- type: ndcg_at_3
value: 34.473
- type: ndcg_at_5
value: 36.561
- type: precision_at_1
value: 27.357
- type: precision_at_10
value: 6.081
- type: precision_at_100
value: 0.9299999999999999
- type: precision_at_1000
value: 0.124
- type: precision_at_3
value: 14.911
- type: precision_at_5
value: 10.24
- type: recall_at_1
value: 24.75
- type: recall_at_10
value: 51.856
- type: recall_at_100
value: 76.44300000000001
- type: recall_at_1000
value: 92.078
- type: recall_at_3
value: 39.427
- type: recall_at_5
value: 44.639
- type: main_score
value: 46.593999999999994
- task:
type: Retrieval
dataset:
name: MTEB ClimateFEVER
type: mteb/climate-fever
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.436
- type: map_at_10
value: 29.693
- type: map_at_100
value: 32.179
- type: map_at_1000
value: 32.353
- type: map_at_3
value: 24.556
- type: map_at_5
value: 27.105
- type: mrr_at_1
value: 37.524
- type: mrr_at_10
value: 51.475
- type: mrr_at_100
value: 52.107000000000006
- type: mrr_at_1000
value: 52.123
- type: mrr_at_3
value: 48.35
- type: mrr_at_5
value: 50.249
- type: ndcg_at_1
value: 37.524
- type: ndcg_at_10
value: 40.258
- type: ndcg_at_100
value: 48.364000000000004
- type: ndcg_at_1000
value: 51.031000000000006
- type: ndcg_at_3
value: 33.359
- type: ndcg_at_5
value: 35.573
- type: precision_at_1
value: 37.524
- type: precision_at_10
value: 12.886000000000001
- type: precision_at_100
value: 2.169
- type: precision_at_1000
value: 0.268
- type: precision_at_3
value: 25.624000000000002
- type: precision_at_5
value: 19.453
- type: recall_at_1
value: 16.436
- type: recall_at_10
value: 47.77
- type: recall_at_100
value: 74.762
- type: recall_at_1000
value: 89.316
- type: recall_at_3
value: 30.508000000000003
- type: recall_at_5
value: 37.346000000000004
- type: main_score
value: 40.258
- task:
type: Retrieval
dataset:
name: MTEB DBPedia
type: mteb/dbpedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 10.147
- type: map_at_10
value: 24.631
- type: map_at_100
value: 35.657
- type: map_at_1000
value: 37.824999999999996
- type: map_at_3
value: 16.423
- type: map_at_5
value: 19.666
- type: mrr_at_1
value: 76.5
- type: mrr_at_10
value: 82.793
- type: mrr_at_100
value: 83.015
- type: mrr_at_1000
value: 83.021
- type: mrr_at_3
value: 81.75
- type: mrr_at_5
value: 82.375
- type: ndcg_at_1
value: 64.75
- type: ndcg_at_10
value: 51.031000000000006
- type: ndcg_at_100
value: 56.005
- type: ndcg_at_1000
value: 63.068000000000005
- type: ndcg_at_3
value: 54.571999999999996
- type: ndcg_at_5
value: 52.66499999999999
- type: precision_at_1
value: 76.5
- type: precision_at_10
value: 42.15
- type: precision_at_100
value: 13.22
- type: precision_at_1000
value: 2.5989999999999998
- type: precision_at_3
value: 58.416999999999994
- type: precision_at_5
value: 52.2
- type: recall_at_1
value: 10.147
- type: recall_at_10
value: 30.786
- type: recall_at_100
value: 62.873000000000005
- type: recall_at_1000
value: 85.358
- type: recall_at_3
value: 17.665
- type: recall_at_5
value: 22.088
- type: main_score
value: 51.031000000000006
- task:
type: Retrieval
dataset:
name: MTEB FEVER
type: mteb/fever
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 78.52900000000001
- type: map_at_10
value: 87.24199999999999
- type: map_at_100
value: 87.446
- type: map_at_1000
value: 87.457
- type: map_at_3
value: 86.193
- type: map_at_5
value: 86.898
- type: mrr_at_1
value: 84.518
- type: mrr_at_10
value: 90.686
- type: mrr_at_100
value: 90.73
- type: mrr_at_1000
value: 90.731
- type: mrr_at_3
value: 90.227
- type: mrr_at_5
value: 90.575
- type: ndcg_at_1
value: 84.518
- type: ndcg_at_10
value: 90.324
- type: ndcg_at_100
value: 90.96300000000001
- type: ndcg_at_1000
value: 91.134
- type: ndcg_at_3
value: 88.937
- type: ndcg_at_5
value: 89.788
- type: precision_at_1
value: 84.518
- type: precision_at_10
value: 10.872
- type: precision_at_100
value: 1.1440000000000001
- type: precision_at_1000
value: 0.117
- type: precision_at_3
value: 34.108
- type: precision_at_5
value: 21.154999999999998
- type: recall_at_1
value: 78.52900000000001
- type: recall_at_10
value: 96.123
- type: recall_at_100
value: 98.503
- type: recall_at_1000
value: 99.518
- type: recall_at_3
value: 92.444
- type: recall_at_5
value: 94.609
- type: main_score
value: 90.324
- task:
type: Retrieval
dataset:
name: MTEB FiQA2018
type: mteb/fiqa
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 29.38
- type: map_at_10
value: 50.28
- type: map_at_100
value: 52.532999999999994
- type: map_at_1000
value: 52.641000000000005
- type: map_at_3
value: 43.556
- type: map_at_5
value: 47.617
- type: mrr_at_1
value: 56.79
- type: mrr_at_10
value: 65.666
- type: mrr_at_100
value: 66.211
- type: mrr_at_1000
value: 66.226
- type: mrr_at_3
value: 63.452
- type: mrr_at_5
value: 64.895
- type: ndcg_at_1
value: 56.79
- type: ndcg_at_10
value: 58.68
- type: ndcg_at_100
value: 65.22
- type: ndcg_at_1000
value: 66.645
- type: ndcg_at_3
value: 53.981
- type: ndcg_at_5
value: 55.95
- type: precision_at_1
value: 56.79
- type: precision_at_10
value: 16.311999999999998
- type: precision_at_100
value: 2.316
- type: precision_at_1000
value: 0.258
- type: precision_at_3
value: 36.214
- type: precision_at_5
value: 27.067999999999998
- type: recall_at_1
value: 29.38
- type: recall_at_10
value: 66.503
- type: recall_at_100
value: 89.885
- type: recall_at_1000
value: 97.954
- type: recall_at_3
value: 48.866
- type: recall_at_5
value: 57.60999999999999
- type: main_score
value: 58.68
- task:
type: Retrieval
dataset:
name: MTEB HotpotQA
type: mteb/hotpotqa
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 42.134
- type: map_at_10
value: 73.412
- type: map_at_100
value: 74.144
- type: map_at_1000
value: 74.181
- type: map_at_3
value: 70.016
- type: map_at_5
value: 72.174
- type: mrr_at_1
value: 84.267
- type: mrr_at_10
value: 89.18599999999999
- type: mrr_at_100
value: 89.29599999999999
- type: mrr_at_1000
value: 89.298
- type: mrr_at_3
value: 88.616
- type: mrr_at_5
value: 88.957
- type: ndcg_at_1
value: 84.267
- type: ndcg_at_10
value: 80.164
- type: ndcg_at_100
value: 82.52199999999999
- type: ndcg_at_1000
value: 83.176
- type: ndcg_at_3
value: 75.616
- type: ndcg_at_5
value: 78.184
- type: precision_at_1
value: 84.267
- type: precision_at_10
value: 16.916
- type: precision_at_100
value: 1.872
- type: precision_at_1000
value: 0.196
- type: precision_at_3
value: 49.71
- type: precision_at_5
value: 31.854
- type: recall_at_1
value: 42.134
- type: recall_at_10
value: 84.578
- type: recall_at_100
value: 93.606
- type: recall_at_1000
value: 97.86
- type: recall_at_3
value: 74.564
- type: recall_at_5
value: 79.635
- type: main_score
value: 80.164
- task:
type: Retrieval
dataset:
name: MTEB MSMARCO
type: mteb/msmarco
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 22.276
- type: map_at_10
value: 35.493
- type: map_at_100
value: 36.656
- type: map_at_1000
value: 36.699
- type: map_at_3
value: 31.320999999999998
- type: map_at_5
value: 33.772999999999996
- type: mrr_at_1
value: 22.966
- type: mrr_at_10
value: 36.074
- type: mrr_at_100
value: 37.183
- type: mrr_at_1000
value: 37.219
- type: mrr_at_3
value: 31.984
- type: mrr_at_5
value: 34.419
- type: ndcg_at_1
value: 22.966
- type: ndcg_at_10
value: 42.895
- type: ndcg_at_100
value: 48.453
- type: ndcg_at_1000
value: 49.464999999999996
- type: ndcg_at_3
value: 34.410000000000004
- type: ndcg_at_5
value: 38.78
- type: precision_at_1
value: 22.966
- type: precision_at_10
value: 6.88
- type: precision_at_100
value: 0.966
- type: precision_at_1000
value: 0.105
- type: precision_at_3
value: 14.785
- type: precision_at_5
value: 11.074
- type: recall_at_1
value: 22.276
- type: recall_at_10
value: 65.756
- type: recall_at_100
value: 91.34100000000001
- type: recall_at_1000
value: 98.957
- type: recall_at_3
value: 42.67
- type: recall_at_5
value: 53.161
- type: main_score
value: 42.895
- task:
type: Retrieval
dataset:
name: MTEB NFCorpus
type: mteb/nfcorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 7.188999999999999
- type: map_at_10
value: 16.176
- type: map_at_100
value: 20.504
- type: map_at_1000
value: 22.203999999999997
- type: map_at_3
value: 11.766
- type: map_at_5
value: 13.655999999999999
- type: mrr_at_1
value: 55.418
- type: mrr_at_10
value: 62.791
- type: mrr_at_100
value: 63.339
- type: mrr_at_1000
value: 63.369
- type: mrr_at_3
value: 60.99099999999999
- type: mrr_at_5
value: 62.059
- type: ndcg_at_1
value: 53.715
- type: ndcg_at_10
value: 41.377
- type: ndcg_at_100
value: 37.999
- type: ndcg_at_1000
value: 46.726
- type: ndcg_at_3
value: 47.262
- type: ndcg_at_5
value: 44.708999999999996
- type: precision_at_1
value: 55.108000000000004
- type: precision_at_10
value: 30.154999999999998
- type: precision_at_100
value: 9.582
- type: precision_at_1000
value: 2.2720000000000002
- type: precision_at_3
value: 43.55
- type: precision_at_5
value: 38.204
- type: recall_at_1
value: 7.188999999999999
- type: recall_at_10
value: 20.655
- type: recall_at_100
value: 38.068000000000005
- type: recall_at_1000
value: 70.208
- type: recall_at_3
value: 12.601
- type: recall_at_5
value: 15.573999999999998
- type: main_score
value: 41.377
- task:
type: Retrieval
dataset:
name: MTEB NQ
type: mteb/nq
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 46.017
- type: map_at_10
value: 62.910999999999994
- type: map_at_100
value: 63.526
- type: map_at_1000
value: 63.536
- type: map_at_3
value: 59.077999999999996
- type: map_at_5
value: 61.521
- type: mrr_at_1
value: 51.68000000000001
- type: mrr_at_10
value: 65.149
- type: mrr_at_100
value: 65.542
- type: mrr_at_1000
value: 65.55
- type: mrr_at_3
value: 62.49
- type: mrr_at_5
value: 64.178
- type: ndcg_at_1
value: 51.651
- type: ndcg_at_10
value: 69.83500000000001
- type: ndcg_at_100
value: 72.18
- type: ndcg_at_1000
value: 72.393
- type: ndcg_at_3
value: 63.168
- type: ndcg_at_5
value: 66.958
- type: precision_at_1
value: 51.651
- type: precision_at_10
value: 10.626
- type: precision_at_100
value: 1.195
- type: precision_at_1000
value: 0.121
- type: precision_at_3
value: 28.012999999999998
- type: precision_at_5
value: 19.09
- type: recall_at_1
value: 46.017
- type: recall_at_10
value: 88.345
- type: recall_at_100
value: 98.129
- type: recall_at_1000
value: 99.696
- type: recall_at_3
value: 71.531
- type: recall_at_5
value: 80.108
- type: main_score
value: 69.83500000000001
- task:
type: Retrieval
dataset:
name: MTEB QuoraRetrieval
type: mteb/quora
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 72.473
- type: map_at_10
value: 86.72800000000001
- type: map_at_100
value: 87.323
- type: map_at_1000
value: 87.332
- type: map_at_3
value: 83.753
- type: map_at_5
value: 85.627
- type: mrr_at_1
value: 83.39
- type: mrr_at_10
value: 89.149
- type: mrr_at_100
value: 89.228
- type: mrr_at_1000
value: 89.229
- type: mrr_at_3
value: 88.335
- type: mrr_at_5
value: 88.895
- type: ndcg_at_1
value: 83.39
- type: ndcg_at_10
value: 90.109
- type: ndcg_at_100
value: 91.09
- type: ndcg_at_1000
value: 91.13900000000001
- type: ndcg_at_3
value: 87.483
- type: ndcg_at_5
value: 88.942
- type: precision_at_1
value: 83.39
- type: precision_at_10
value: 13.711
- type: precision_at_100
value: 1.549
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 38.342999999999996
- type: precision_at_5
value: 25.188
- type: recall_at_1
value: 72.473
- type: recall_at_10
value: 96.57
- type: recall_at_100
value: 99.792
- type: recall_at_1000
value: 99.99900000000001
- type: recall_at_3
value: 88.979
- type: recall_at_5
value: 93.163
- type: main_score
value: 90.109
- task:
type: Retrieval
dataset:
name: MTEB SCIDOCS
type: mteb/scidocs
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.598
- type: map_at_10
value: 11.405999999999999
- type: map_at_100
value: 13.447999999999999
- type: map_at_1000
value: 13.758999999999999
- type: map_at_3
value: 8.332
- type: map_at_5
value: 9.709
- type: mrr_at_1
value: 22.6
- type: mrr_at_10
value: 32.978
- type: mrr_at_100
value: 34.149
- type: mrr_at_1000
value: 34.213
- type: mrr_at_3
value: 29.7
- type: mrr_at_5
value: 31.485000000000003
- type: ndcg_at_1
value: 22.6
- type: ndcg_at_10
value: 19.259999999999998
- type: ndcg_at_100
value: 27.21
- type: ndcg_at_1000
value: 32.7
- type: ndcg_at_3
value: 18.445
- type: ndcg_at_5
value: 15.812000000000001
- type: precision_at_1
value: 22.6
- type: precision_at_10
value: 9.959999999999999
- type: precision_at_100
value: 2.139
- type: precision_at_1000
value: 0.345
- type: precision_at_3
value: 17.299999999999997
- type: precision_at_5
value: 13.719999999999999
- type: recall_at_1
value: 4.598
- type: recall_at_10
value: 20.186999999999998
- type: recall_at_100
value: 43.362
- type: recall_at_1000
value: 70.11800000000001
- type: recall_at_3
value: 10.543
- type: recall_at_5
value: 13.923
- type: main_score
value: 19.259999999999998
- task:
type: Retrieval
dataset:
name: MTEB SciFact
type: mteb/scifact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 65.467
- type: map_at_10
value: 74.935
- type: map_at_100
value: 75.395
- type: map_at_1000
value: 75.412
- type: map_at_3
value: 72.436
- type: map_at_5
value: 73.978
- type: mrr_at_1
value: 68.667
- type: mrr_at_10
value: 76.236
- type: mrr_at_100
value: 76.537
- type: mrr_at_1000
value: 76.55499999999999
- type: mrr_at_3
value: 74.722
- type: mrr_at_5
value: 75.639
- type: ndcg_at_1
value: 68.667
- type: ndcg_at_10
value: 78.92099999999999
- type: ndcg_at_100
value: 80.645
- type: ndcg_at_1000
value: 81.045
- type: ndcg_at_3
value: 75.19500000000001
- type: ndcg_at_5
value: 77.114
- type: precision_at_1
value: 68.667
- type: precision_at_10
value: 10.133000000000001
- type: precision_at_100
value: 1.0999999999999999
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 28.889
- type: precision_at_5
value: 18.8
- type: recall_at_1
value: 65.467
- type: recall_at_10
value: 89.517
- type: recall_at_100
value: 97
- type: recall_at_1000
value: 100
- type: recall_at_3
value: 79.72200000000001
- type: recall_at_5
value: 84.511
- type: main_score
value: 78.92099999999999
- task:
type: Retrieval
dataset:
name: MTEB TRECCOVID
type: mteb/trec-covid
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.244
- type: map_at_10
value: 2.183
- type: map_at_100
value: 13.712
- type: map_at_1000
value: 33.147
- type: map_at_3
value: 0.7270000000000001
- type: map_at_5
value: 1.199
- type: mrr_at_1
value: 94
- type: mrr_at_10
value: 97
- type: mrr_at_100
value: 97
- type: mrr_at_1000
value: 97
- type: mrr_at_3
value: 97
- type: mrr_at_5
value: 97
- type: ndcg_at_1
value: 92
- type: ndcg_at_10
value: 84.399
- type: ndcg_at_100
value: 66.771
- type: ndcg_at_1000
value: 59.092
- type: ndcg_at_3
value: 89.173
- type: ndcg_at_5
value: 88.52600000000001
- type: precision_at_1
value: 94
- type: precision_at_10
value: 86.8
- type: precision_at_100
value: 68.24
- type: precision_at_1000
value: 26.003999999999998
- type: precision_at_3
value: 92.667
- type: precision_at_5
value: 92.4
- type: recall_at_1
value: 0.244
- type: recall_at_10
value: 2.302
- type: recall_at_100
value: 16.622
- type: recall_at_1000
value: 55.175
- type: recall_at_3
value: 0.748
- type: recall_at_5
value: 1.247
- type: main_score
value: 84.399
- task:
type: Retrieval
dataset:
name: MTEB Touche2020
type: mteb/touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.707
- type: map_at_10
value: 10.917
- type: map_at_100
value: 16.308
- type: map_at_1000
value: 17.953
- type: map_at_3
value: 5.65
- type: map_at_5
value: 7.379
- type: mrr_at_1
value: 34.694
- type: mrr_at_10
value: 49.745
- type: mrr_at_100
value: 50.309000000000005
- type: mrr_at_1000
value: 50.32
- type: mrr_at_3
value: 44.897999999999996
- type: mrr_at_5
value: 48.061
- type: ndcg_at_1
value: 33.672999999999995
- type: ndcg_at_10
value: 26.894000000000002
- type: ndcg_at_100
value: 37.423
- type: ndcg_at_1000
value: 49.376999999999995
- type: ndcg_at_3
value: 30.456
- type: ndcg_at_5
value: 27.772000000000002
- type: precision_at_1
value: 34.694
- type: precision_at_10
value: 23.878
- type: precision_at_100
value: 7.489999999999999
- type: precision_at_1000
value: 1.555
- type: precision_at_3
value: 31.293
- type: precision_at_5
value: 26.939
- type: recall_at_1
value: 2.707
- type: recall_at_10
value: 18.104
- type: recall_at_100
value: 46.93
- type: recall_at_1000
value: 83.512
- type: recall_at_3
value: 6.622999999999999
- type: recall_at_5
value: 10.051
- type: main_score
value: 26.894000000000002
VenkatNDivi77/e5-R-mistral-7b-Q4_K_M-GGUF
This model was converted to GGUF format from BeastyZ/e5-R-mistral-7b using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo VenkatNDivi77/e5-R-mistral-7b-Q4_K_M-GGUF --hf-file e5-r-mistral-7b-q4_k_m.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo VenkatNDivi77/e5-R-mistral-7b-Q4_K_M-GGUF --hf-file e5-r-mistral-7b-q4_k_m.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo VenkatNDivi77/e5-R-mistral-7b-Q4_K_M-GGUF --hf-file e5-r-mistral-7b-q4_k_m.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo VenkatNDivi77/e5-R-mistral-7b-Q4_K_M-GGUF --hf-file e5-r-mistral-7b-q4_k_m.gguf -c 2048