Open-weight model · Question answering
Gecko-110m-en
by LiteRT Community (FKA TFLite) litert-community/Gecko-110m-en
This model provides a few variants of the embedding model published in the Gecko paper that are ready for deployment on Android or iOS using LiteRT stack or google ai edge RAG SDK. Try out the gecko embedding model in the google ai edge RAG SDK.
Parameters—
Context—
Weights2.3 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2.2k
Model Card
By LiteRT Community (FKA TFLite), published under apache-2.0, revision 61a0d0c2cdc9.
This model provides a few variants of the embedding model published in the Gecko paper that are ready for deployment on Android or iOS using LiteRT stack or google ai edge RAG SDK. Try out the gecko embedding model in the google ai edge RAG SDK. You can find the SDK on GitHub or follow our android guide to install directly from Maven. We have also published a Use the sentencepiece model as the tokenizer for the Gecko embedding model. Note that all benchmark stats are from a Samsung S23 Ultra. The inference is run on CPU is accelerated via the LiteRT XNNPACK delegate with 4 threads The inference on GPU is accelerated via LiteRT GPU delegate. Benchmark is done assuming XNNPACK cache is…
Read LiteRT Community (FKA TFLite)'s full model card
This model provides a few variants of the embedding model published in the Gecko paper that are ready for deployment on Android or iOS using LiteRT stack or google ai edge RAG SDK.
Use the models
Android
- Try out the gecko embedding model in the google ai edge RAG SDK. You can find the SDK on GitHub or follow our android guide to install directly from Maven. We have also published a sample app.
- Use the sentencepiece model as the tokenizer for the Gecko embedding model.
Performance
Android
Note that all benchmark stats are from a Samsung S23 Ultra.
| Backend | Max sequence length | Init time (ms) | Inference time (ms) | Memory (RSS in MB) | Model size (MB) | |
|---|---|---|---|---|---|---|
dynamic_int8 |
GPU |
256 |
1306.06 |
76.2 |
604.5 |
114 |
dynamic_int8 |
GPU |
512 |
1363.38 |
173.2 |
604.6 |
120 |
dynamic_int8 |
GPU |
1024 |
1419.87 |
397 |
871.1 |
145 |
dynamic_int8 |
CPU |
256 |
11.03 |
147.6 |
126.3 |
114 |
dynamic_int8 |
CPU |
512 |
30.04 |
353.1 |
225.6 |
120 |
dynamic_int8 |
CPU |
1024 |
79.17 |
954 |
619.5 |
145 |
- Model Size: measured by the size of the .tflite flatbuffer (serialization format for LiteRT models)
- Memory: indicator of peak RAM usage
- The inference is run on CPU is accelerated via the LiteRT XNNPACK delegate with 4 threads
- The inference on GPU is accelerated via LiteRT GPU delegate.
- Benchmark is done assuming XNNPACK cache is enabled
- dynamic_int8: quantized model with int8 weights and float activations.
Identity and Version
- Repository
- litert-community/Gecko-110m-en
- Publisher
- LiteRT Community (FKA TFLite)
- Task
- Question answering
- Modality
- Text
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 61a0d0c2cdc9b4f2c1727e63acb7ad86e68508c2
- First published
- 2025-03-11
- Last updated
- 2025-03-12
Files and Weights
11 files, 2.3 GB in total. The weights are 8 files totalling 2.3 GB in tflite.
Weights8 files · 2.3 GB
Documentation1 file · 4.0 KB
Other1 file · 794.3 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Gecko_1024_f32.tflite | Weights | 474.7 MB | d594eebd0dc0 |
| Gecko_1024_quant.tflite | Weights | 145.6 MB | 2334395c8192 |
| Gecko_256_f32.tflite | Weights | 443.2 MB | eb738ab8cd00 |
| Gecko_256_quant.tflite | Weights | 114.1 MB | 81505c2a2968 |
| Gecko_512_f32.tflite | Weights | 449.5 MB | ab5b20c443e6 |
| Gecko_512_quant.tflite | Weights | 120.4 MB | 2b11bb47da36 |
| Gecko_64_f32.tflite | Weights | 441.2 MB | 31e402e85fd0 |
| Gecko_64_quant.tflite | Weights | 112.2 MB | 19f04c9397c8 |
| README.md | Documentation | 4.0 KB | — |
| sentencepiece.model | Other | 794.3 KB | 839ffa4b9afa |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 2.3 GB
Download from LiteRT Community (FKA TFLite)
Released by LiteRT Community (FKA TFLite) through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2403.20327
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Gecko-110m-en
Can I use Gecko-110m-en commercially?
Yes. Gecko-110m-en is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Splinter-base is the pretrained model discussed in the paper Few-Shot Question Answering by Pretraining Span Selection (at ACL 2021). Its original repository can be found here. The model is case-sensitive. Note: This model doesn't contain the pretrained weights for the QASS layer (see paper for details), and therefore the QASS layer is randomly initialized upon loading it. For the model with those weights, see tau/splinter-base-qass. Splinter is a model that is pretrained in a self-supervised fashion for few-shot question answering. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an…
This model can be used for the task of question answering. The model should not be used to intentionally create hostile or alienating environments for people. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. The model creators note in the associated paper: The model creators note in the associated paper: The model…
This model is a fine-tune checkpoint of DistilBERT-base-cased, fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1. This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).
This model can be used for the task of Question Answering on Legal Documents. Read: An Open Source Contractual Language Understanding Application Using Machine Learning for detailed information on training procedure, dataset preprocessing and evaluation. See CUAD dataset card for more information. See CUAD dataset card for more information. Used V100/P100 from Google Colab Pro Python, Transformers Mohammed Rakib in collaboration with Ezi Ozoani and the Hugging Face team Use the code below to get started with the model.