Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 24 layers and the embedding size is 1024. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. Below is an example for usage with sentencetransformers. Package requirements pip install sentencetransformers~=2.2.2 1. Do I need to add the prefix "query: " and "passage: " to input texts? Yes, this is how the model is trained, otherwise you will see a performance degradation.…
KielEmbed-Pro is an open-weight model for sentence similarity from Tech. It has 335M parameters and a 512-token context. At 16-bit it needs about 0.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 33 downloads a month.
This is a sentence-transformers model finetuned from BAAI/bge-large-en-v1.5. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.
Parameters335M
Context512
Weights1.3 GB
License—
AccessOpen weights
Monthly Downloads33
Runs On
What it takes to serve KielEmbed-Pro (335M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.7 GB | 0.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 23, 2026.
KielEmbed-Pro on every accelerator the SAVRN Index prices, at every precision
Model Card
This is a sentence-transformers model finetuned from BAAI/bge-large-en-v1.5. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval. First install the Sentence Transformers library: Then you can load this model and run inference. Approximate statistics based on the first 1000 samples: - perdevicetrainbatchsize: 2 - gradientaccumulationsteps: 16 - learningrate: 2e-05 - numtrainepochs: 1 - warmupsteps: 0.1 - fp16: True - gradientcheckpointing: True - dopredict: False - predictionlossonly: True - perdevicetrainbatchsize: 2 - perdeviceevalbatchsize: 8 - gradientaccumulationsteps: 16 - evalaccumulationsteps: None - torchemptycachesteps: None…
Excerpt from the card by Tech.
Configuration
- Architecture
- BertModel
- Context length (tokens)
- 512
- Layers
- 24
- Hidden size
- 1,024
- Feed-forward size
- 4,096
- Attention heads
- 16
- Vocabulary size
- 30,522
- Model type
- bert
Identity and Version
- Repository
- kiel2/KielEmbed-Pro
- Publisher
- Tech
- Task
- Sentence similarity
- Modality
- Text
- Library
- sentence-transformers
- Parameters
- 335M parameters
- Languages
- Not stated by the source
- Revision
- ec849fc9d0da12b679e2d554f471642ad32e101c
- First published
- 2026-09-21
- Last updated
- 2026-09-23
Files and Weights
11 files, 1.3 GB in total. The weights are 1 file totalling 1.3 GB in safetensors.
Weights1 file · 1.3 GB
Configuration6 files · 2.0 KB
Tokenizer2 files · 712.2 KB
Documentation1 file · 14.9 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.3 GB | 63aeb899b73c |
| 1_Pooling/config.json | Configuration | 90 B | — |
| 2_Normalize/config.json | Configuration | 97 B | — |
| config.json | Configuration | 824 B | — |
| config_sentence_transformers.json | Configuration | 320 B | — |
| modules.json | Configuration | 429 B | — |
| sentence_bert_config.json | Configuration | 241 B | — |
| README.md | Documentation | 14.9 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 711.8 KB | — |
| tokenizer_config.json | Tokenizer | 414 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.3 GB
Download from Tech
Released by Tech through its official repository on Hugging Face.
Built From
- Derived from BAAI/bge-large-en-v1.5
- Described by arXiv:1807.03748
- Described by arXiv:1908.10084
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.3 GB |
| 16-bit | 0.7 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About KielEmbed-Pro
How much GPU memory does KielEmbed-Pro need?
About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (335M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run KielEmbed-Pro on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is KielEmbed-Pro's context length?
512 tokens, from the maximum position embeddings in its published configuration.
Similar Models
General Text Embeddings (GTE) model. Towards General Text Embeddings with Multi-stage Contrastive Learning The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc. We compared the performance of the GTE models with other popular text embedding models on the MTEB…
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…
This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained roberta-large model and…
The gte-multilingual-base model is the latest in the GTE (General Text Embedding) family of models, featuring several key attributes: Paper: mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval - It is recommended to install xformers and enable unpadding for acceleration, refer to enable-unpadding-and-xformers. - How to use with TEI: refs/pr/7 Usage via docker and infinity, MIT Licensed. Usage via Docker and Text Embeddings Inference (TEI): Then you can send requests to the deployed API via the OpenAI-compatible v1/embeddings route (more information about the OpenAI Embeddings API): We validated the performance of the gte-multilingual-base…