---
quantized_by: bartowski
pipeline_tag: text-generation
language:
- en
- ar
- cs
- de
- es
- fr
- it
- ja
- ko
- nl
- pt
- zh
tags:
- language
- granite
- embeddings
- multilingual
license: apache-2.0
base_model: ibm-granite/granite-embedding-107m-multilingual
model-index:
- name: ibm-granite/granite-embedding-107m-multilingual
results:
- task:
type: Retrieval
dataset:
name: Miracl (en)
type: miracl/mmteb-miracl
config: en
split: dev
metrics:
- type: ndcg_at_1
value: 0.41176
- type: ndcg_at_10
value: 0.46682
- type: ndcg_at_100
value: 0.54326
- type: ndcg_at_1000
value: 0.56567
- type: ndcg_at_20
value: 0.50157
- type: ndcg_at_3
value: 0.41197
- type: ndcg_at_5
value: 0.42086
- type: recall_at_1
value: 0.19322
- type: recall_at_10
value: 0.57721
- type: recall_at_100
value: 0.83256
- type: recall_at_1000
value: 0.95511
- type: recall_at_20
value: 0.6757
- type: recall_at_3
value: 0.37171
- type: recall_at_5
value: 0.44695
- task:
type: Retrieval
dataset:
name: Miracl (ar)
type: miracl/mmteb-miracl
config: ar
split: dev
metrics:
- type: ndcg_at_1
value: 0.55559
- type: ndcg_at_10
value: 0.62541
- type: ndcg_at_100
value: 0.67101
- type: ndcg_at_1000
value: 0.6805
- type: ndcg_at_20
value: 0.64739
- type: ndcg_at_3
value: 0.56439
- type: ndcg_at_5
value: 0.59347
- type: recall_at_1
value: 0.37009
- type: recall_at_10
value: 0.73317
- type: recall_at_100
value: 0.90066
- type: recall_at_1000
value: 0.96272
- type: recall_at_20
value: 0.80205
- type: recall_at_3
value: 0.56903
- type: recall_at_5
value: 0.6518
- task:
type: Retrieval
dataset:
name: Miracl (bn)
type: miracl/mmteb-miracl
config: bn
split: dev
metrics:
- type: ndcg_at_1
value: 0.56691
- type: ndcg_at_10
value: 0.65484
- type: ndcg_at_100
value: 0.70142
- type: ndcg_at_1000
value: 0.70994
- type: ndcg_at_20
value: 0.67838
- type: ndcg_at_3
value: 0.5988
- type: ndcg_at_5
value: 0.62718
- type: recall_at_1
value: 0.3605
- type: recall_at_10
value: 0.76854
- type: recall_at_100
value: 0.9285
- type: recall_at_1000
value: 0.97928
- type: recall_at_20
value: 0.83667
- type: recall_at_3
value: 0.61596
- type: recall_at_5
value: 0.69766
- task:
type: Retrieval
dataset:
name: Miracl (de)
type: miracl/mmteb-miracl
config: de
split: dev
metrics:
- type: ndcg_at_1
value: 0.41967
- type: ndcg_at_10
value: 0.45141
- type: ndcg_at_100
value: 0.53461
- type: ndcg_at_1000
value: 0.55463
- type: ndcg_at_20
value: 0.49012
- type: ndcg_at_3
value: 0.39486
- type: ndcg_at_5
value: 0.41496
- type: recall_at_1
value: 0.19494
- type: recall_at_10
value: 0.53774
- type: recall_at_100
value: 0.83314
- type: recall_at_1000
value: 0.95045
- type: recall_at_20
value: 0.65659
- type: recall_at_3
value: 0.3556
- type: recall_at_5
value: 0.44448
- task:
type: Retrieval
dataset:
name: Miracl (es)
type: miracl/mmteb-miracl
config: es
split: dev
metrics:
- type: ndcg_at_1
value: 0.54475
- type: ndcg_at_10
value: 0.46593
- type: ndcg_at_100
value: 0.58079
- type: ndcg_at_1000
value: 0.60656
- type: ndcg_at_20
value: 0.51858
- type: ndcg_at_3
value: 0.4578
- type: ndcg_at_5
value: 0.44321
- type: recall_at_1
value: 0.15966
- type: recall_at_10
value: 0.49343
- type: recall_at_100
value: 0.82684
- type: recall_at_1000
value: 0.95299
- type: recall_at_20
value: 0.62367
- type: recall_at_3
value: 0.2949
- type: recall_at_5
value: 0.37983
- task:
type: Retrieval
dataset:
name: Miracl (fa)
type: miracl/mmteb-miracl
config: fa
split: dev
metrics:
- type: ndcg_at_1
value: 0.36709
- type: ndcg_at_10
value: 0.46961
- type: ndcg_at_100
value: 0.53262
- type: ndcg_at_1000
value: 0.55024
- type: ndcg_at_20
value: 0.49892
- type: ndcg_at_3
value: 0.40235
- type: ndcg_at_5
value: 0.42866
- type: recall_at_1
value: 0.22735
- type: recall_at_10
value: 0.59949
- type: recall_at_100
value: 0.83867
- type: recall_at_1000
value: 0.95007
- type: recall_at_20
value: 0.68947
- type: recall_at_3
value: 0.41781
- type: recall_at_5
value: 0.49374
- task:
type: Retrieval
dataset:
name: Miracl (fi)
type: miracl/mmteb-miracl
config: fi
split: dev
metrics:
- type: ndcg_at_1
value: 0.59245
- type: ndcg_at_10
value: 0.65551
- type: ndcg_at_100
value: 0.6967
- type: ndcg_at_1000
value: 0.70521
- type: ndcg_at_20
value: 0.67552
- type: ndcg_at_3
value: 0.58876
- type: ndcg_at_5
value: 0.61779
- type: recall_at_1
value: 0.37669
- type: recall_at_10
value: 0.76529
- type: recall_at_100
value: 0.9156
- type: recall_at_1000
value: 0.96977
- type: recall_at_20
value: 0.82685
- type: recall_at_3
value: 0.60234
- type: recall_at_5
value: 0.67135
- task:
type: Retrieval
dataset:
name: Miracl (fr)
type: miracl/mmteb-miracl
config: fr
split: dev
metrics:
- type: ndcg_at_1
value: 0.38776
- type: ndcg_at_10
value: 0.47589
- type: ndcg_at_100
value: 0.54641
- type: ndcg_at_1000
value: 0.5629
- type: ndcg_at_20
value: 0.51203
- type: ndcg_at_3
value: 0.38924
- type: ndcg_at_5
value: 0.42572
- type: recall_at_1
value: 0.22082
- type: recall_at_10
value: 0.61619
- type: recall_at_100
value: 0.87237
- type: recall_at_1000
value: 0.97449
- type: recall_at_20
value: 0.72689
- type: recall_at_3
value: 0.39527
- type: recall_at_5
value: 0.48983
- task:
type: Retrieval
dataset:
name: Miracl (hi)
type: miracl/mmteb-miracl
config: hi
split: dev
metrics:
- type: ndcg_at_1
value: 0.33143
- type: ndcg_at_10
value: 0.42084
- type: ndcg_at_100
value: 0.48647
- type: ndcg_at_1000
value: 0.50712
- type: ndcg_at_20
value: 0.45399
- type: ndcg_at_3
value: 0.34988
- type: ndcg_at_5
value: 0.37938
- type: recall_at_1
value: 0.17852
- type: recall_at_10
value: 0.55217
- type: recall_at_100
value: 0.79929
- type: recall_at_1000
value: 0.93434
- type: recall_at_20
value: 0.65231
- type: recall_at_3
value: 0.33765
- type: recall_at_5
value: 0.43828
- task:
type: Retrieval
dataset:
name: Miracl (id)
type: miracl/mmteb-miracl
config: id
split: dev
metrics:
- type: ndcg_at_1
value: 0.43854
- type: ndcg_at_10
value: 0.45459
- type: ndcg_at_100
value: 0.53643
- type: ndcg_at_1000
value: 0.56052
- type: ndcg_at_20
value: 0.48795
- type: ndcg_at_3
value: 0.41041
- type: ndcg_at_5
value: 0.42235
- type: recall_at_1
value: 0.19193
- type: recall_at_10
value: 0.5289
- type: recall_at_100
value: 0.79649
- type: recall_at_1000
value: 0.92937
- type: recall_at_20
value: 0.61813
- type: recall_at_3
value: 0.35431
- type: recall_at_5
value: 0.43348
- task:
type: Retrieval
dataset:
name: Miracl (ja)
type: miracl/mmteb-miracl
config: ja
split: dev
metrics:
- type: ndcg_at_1
value: 0.53256
- type: ndcg_at_10
value: 0.59922
- type: ndcg_at_100
value: 0.65407
- type: ndcg_at_1000
value: 0.66484
- type: ndcg_at_20
value: 0.62596
- type: ndcg_at_3
value: 0.53717
- type: ndcg_at_5
value: 0.56523
- type: recall_at_1
value: 0.34555
- type: recall_at_10
value: 0.71476
- type: recall_at_100
value: 0.91152
- type: recall_at_1000
value: 0.97728
- type: recall_at_20
value: 0.79811
- type: recall_at_3
value: 0.53482
- type: recall_at_5
value: 0.62327
- task:
type: Retrieval
dataset:
name: Miracl (ko)
type: miracl/mmteb-miracl
config: ko
split: dev
metrics:
- type: ndcg_at_1
value: 0.5493
- type: ndcg_at_10
value: 0.58413
- type: ndcg_at_100
value: 0.64374
- type: ndcg_at_1000
value: 0.65655
- type: ndcg_at_20
value: 0.61732
- type: ndcg_at_3
value: 0.53068
- type: ndcg_at_5
value: 0.55202
- type: recall_at_1
value: 0.32602
- type: recall_at_10
value: 0.68647
- type: recall_at_100
value: 0.87746
- type: recall_at_1000
value: 0.95524
- type: recall_at_20
value: 0.78089
- type: recall_at_3
value: 0.49173
- type: recall_at_5
value: 0.5827
- task:
type: Retrieval
dataset:
name: Miracl (ru)
type: miracl/mmteb-miracl
config: ru
split: dev
metrics:
- type: ndcg_at_1
value: 0.43131
- type: ndcg_at_10
value: 0.48262
- type: ndcg_at_100
value: 0.56158
- type: ndcg_at_1000
value: 0.57929
- type: ndcg_at_20
value: 0.52023
- type: ndcg_at_3
value: 0.42808
- type: ndcg_at_5
value: 0.44373
- type: recall_at_1
value: 0.22018
- type: recall_at_10
value: 0.58034
- type: recall_at_100
value: 0.84074
- type: recall_at_1000
value: 0.93938
- type: recall_at_20
value: 0.68603
- type: recall_at_3
value: 0.39307
- type: recall_at_5
value: 0.47077
- task:
type: Retrieval
dataset:
name: Miracl (sw)
type: miracl/mmteb-miracl
config: sw
split: dev
metrics:
- type: ndcg_at_1
value: 0.50415
- type: ndcg_at_10
value: 0.59111
- type: ndcg_at_100
value: 0.64312
- type: ndcg_at_1000
value: 0.65089
- type: ndcg_at_20
value: 0.61651
- type: ndcg_at_3
value: 0.5304
- type: ndcg_at_5
value: 0.56139
- type: recall_at_1
value: 0.33267
- type: recall_at_10
value: 0.72082
- type: recall_at_100
value: 0.91377
- type: recall_at_1000
value: 0.96152
- type: recall_at_20
value: 0.79943
- type: recall_at_3
value: 0.5548
- type: recall_at_5
value: 0.64302
- task:
type: Retrieval
dataset:
name: Miracl (te)
type: miracl/mmteb-miracl
config: te
split: dev
metrics:
- type: ndcg_at_1
value: 0.64372
- type: ndcg_at_10
value: 0.78175
- type: ndcg_at_100
value: 0.79523
- type: ndcg_at_1000
value: 0.79774
- type: ndcg_at_20
value: 0.78826
- type: ndcg_at_3
value: 0.74856
- type: ndcg_at_5
value: 0.77128
- type: recall_at_1
value: 0.63688
- type: recall_at_10
value: 0.90358
- type: recall_at_100
value: 0.96558
- type: recall_at_1000
value: 0.9847
- type: recall_at_20
value: 0.92834
- type: recall_at_3
value: 0.81804
- type: recall_at_5
value: 0.87198
- task:
type: Retrieval
dataset:
name: Miracl (th)
type: miracl/mmteb-miracl
config: th
split: dev
metrics:
- type: ndcg_at_1
value: 0.65484
- type: ndcg_at_10
value: 0.71774
- type: ndcg_at_100
value: 0.75362
- type: ndcg_at_1000
value: 0.75898
- type: ndcg_at_20
value: 0.73709
- type: ndcg_at_3
value: 0.66199
- type: ndcg_at_5
value: 0.68451
- type: recall_at_1
value: 0.45911
- type: recall_at_10
value: 0.82619
- type: recall_at_100
value: 0.95515
- type: recall_at_1000
value: 0.98854
- type: recall_at_20
value: 0.88447
- type: recall_at_3
value: 0.67437
- type: recall_at_5
value: 0.73786
- task:
type: Retrieval
dataset:
name: Miracl (yo)
type: miracl/mmteb-miracl
config: yo
split: dev
metrics:
- type: ndcg_at_1
value: 0.46218
- type: ndcg_at_10
value: 0.64685
- type: ndcg_at_100
value: 0.66941
- type: ndcg_at_1000
value: 0.67361
- type: ndcg_at_20
value: 0.65548
- type: ndcg_at_3
value: 0.57609
- type: ndcg_at_5
value: 0.62021
- type: recall_at_1
value: 0.42787
- type: recall_at_10
value: 0.82913
- type: recall_at_100
value: 0.93277
- type: recall_at_1000
value: 0.96499
- type: recall_at_20
value: 0.85994
- type: recall_at_3
value: 0.65406
- type: recall_at_5
value: 0.7542
- task:
type: Retrieval
dataset:
name: Miracl (zh)
type: miracl/mmteb-miracl
config: zh
split: dev
metrics:
- type: ndcg_at_1
value: 0.41985
- type: ndcg_at_10
value: 0.4837
- type: ndcg_at_100
value: 0.55961
- type: ndcg_at_1000
value: 0.5762
- type: ndcg_at_20
value: 0.51595
- type: ndcg_at_3
value: 0.42094
- type: ndcg_at_5
value: 0.44273
- type: recall_at_1
value: 0.21446
- type: recall_at_10
value: 0.59695
- type: recall_at_100
value: 0.87388
- type: recall_at_1000
value: 0.96833
- type: recall_at_20
value: 0.69252
- type: recall_at_3
value: 0.40377
- type: recall_at_5
value: 0.4903
---
## 💫 Community Model> granite embedding 107m multilingual by Ibm-Granite
*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [ibm-granite](https://huggingface.co/ibm-granite)
**Original model**: [granite-embedding-107m-multilingual](https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual)
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b4381](https://github.com/ggerganov/llama.cpp/releases/tag/b4381)
## Technical Details
Embedding model with vector size 384
Max length of 512 tokens
107 million parameters for high quality fast embedding
Supported Languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.