# Feature Extraction Models: Open-Weight AI Source: https://savrn.com/models/tasks/feature-extraction Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Feature Extraction Models 398 open-weight feature extraction models in the SAVRN Model Hub, with Quan, Alex Kroman and Beijing Academy of Artificial Intelligence publishing the most. 398Models 329Publishers 627K to 29.8BParameter range 7Licenses ## SAVRN's Take Every retrieval pipeline we stand up starts with one of these. A feature extraction model turns a passage of text, or in one case audio, into a fixed-length vector a database can compare against millions of others, which is how semantic search finds the right chunk. The Beijing Academy of Artificial Intelligence leads the 77 entries with 8 models, and its bge-small-en-v1.5 pulls 64,516,396 downloads a month, more than five times the 11,607,634 of bge-large-en-v1.5. Qwen and Jina AI follow with 3 each. Hardware is the easy part. bge-small-en-v1.5 needs 0.1 GB at 16-bit, and even Qwen3-Embedding-8B at 7.6B parameters fits in 18.2 GB, or 4.5 GB at 4-bit. The cheapest Index host for all of them is a single MI300X at $1.85 an hour, so the question in our facilities is how much of a card to give the embedding service beside the generation model it feeds. Context length is where the choices separate: the BGE English models stop at 512 tokens, which means chunking every document, while granite-embedding-small-english-r2 takes 8,192 in 48M parameters and the Qwen3 embedding models take 32,768 at 0.6B and 40,960 at 8B. Licensing rarely blocks a deployment. 54 of the 77 are MIT and 15 are Apache-2.0, both fine for commercial use. Seven state no license and one is cc-by-nc-4.0, so check those eight first. Then weigh vector width: the Granite model emits 384 dimensions, multilingual-e5-large 1024, and the wider vector costs more to store per chunk. Weigh language too: bge v1.5 comes in English and Chinese editions, and multilingual-e5-large covers 100 languages. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [bge-small-en-v1.5](https://savrn.com/models/bge-small-en-v1-5) | Beijing Academy of Artificial Intelligence | 33M | mit | 55.4M | 1x MI300X, $1.85/hr | | [bge-large-en-v1.5](https://savrn.com/models/bge-large-en-v1-5) | Beijing Academy of Artificial Intelligence | 335M | mit | 9.8M | 1x MI300X, $1.85/hr | | [bge-base-en-v1.5](https://savrn.com/models/bge-base-en-v1-5) | Beijing Academy of Artificial Intelligence | 109M | mit | 8.8M | 1x MI300X, $1.85/hr | | [Qwen3-Embedding-0.6B](https://savrn.com/models/qwen3-embedding-0-6b) | Qwen | 596M | apache-2.0 | 8.3M | 1x MI300X, $1.85/hr | | [multilingual-e5-large](https://savrn.com/models/multilingual-e5-large) | Liang Wang | 560M | mit | 6.6M | 1x MI300X, $1.85/hr | | [granite-embedding-small-english-r2](https://savrn.com/models/granite-embedding-small-english-r2) | IBM Granite | 48M | apache-2.0 | 6M | 1x MI300X, $1.85/hr | | [all-MiniLM-L6-v2](https://savrn.com/models/all-minilm-l6-v2-2) | Joshua | — | apache-2.0 | 4.5M | — | | [bge-small-zh-v1.5](https://savrn.com/models/bge-small-zh-v1-5) | Beijing Academy of Artificial Intelligence | 24M | mit | 3.6M | 1x MI300X, $1.85/hr | | [bge-base-en](https://savrn.com/models/bge-base-en) | Beijing Academy of Artificial Intelligence | 109M | mit | 2.4M | 1x MI300X, $1.85/hr | | [bge-base-en-v1.5](https://savrn.com/models/bge-base-en-v1-5-2) | Joshua | — | mit | 2.3M | — | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | [mit](https://savrn.com/models/licenses/mit) | 278 | Yes | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 81 | Yes | | not stated | 22 | Not stated | | other | 8 | Read the license | | [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) | 5 | Not without separate permission | | [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) | 2 | Not without separate permission | | [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) | 2 | Yes | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Quan](https://savrn.com/model-publishers/wq2012) | 30 | | [Alex Kroman](https://savrn.com/model-publishers/mazesmazes) | 8 | | [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) | 8 | | [Jina AI](https://savrn.com/model-publishers/jinaai) | 4 | | [Social Jev](https://savrn.com/model-publishers/social-jev) | 3 | | [RKNNAI](https://savrn.com/model-publishers/rknnai) | 3 | ## All 398 Models, Page 1 of 7 Model · Feature extraction ### [bge-small-en-v1.5](https://savrn.com/models/bge-small-en-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) More details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical… Open weights mit 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-small-en-v1-5) Model · Feature extraction ### [bge-large-en-v1.5](https://savrn.com/models/bge-large-en-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) For more details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model that supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical… Open weights mit 335M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-large-en-v1-5) Model · Feature extraction ### [bge-base-en-v1.5](https://savrn.com/models/bge-base-en-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) For more details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical… Open weights mit 109M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-base-en-v1-5) Model · Feature extraction ### [Qwen3-Embedding-0.6B](https://savrn.com/models/qwen3-embedding-0-6b) [Qwen](https://savrn.com/model-publishers/qwen) The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility: The… Open weights apache-2.0 596M parameters 32,768 tokens sentence-transformers [View model](https://savrn.com/models/qwen3-embedding-0-6b) Model · Feature extraction ### [multilingual-e5-large](https://savrn.com/models/multilingual-e5-large) [Liang Wang](https://savrn.com/model-publishers/intfloat) Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 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. This model is initialized from xlm-roberta-large and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta, but low-resource languages may see performance degradation. For all labeled datasets, we only use its training set for fine-tuning. For other training details, please refer to our paper at https://arxiv.org/pdf/2402.05672. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB… Open weights mit 560M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/multilingual-e5-large) Model · Feature extraction ### [granite-embedding-small-english-r2](https://savrn.com/models/granite-embedding-small-english-r2) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 based on context length of upto 8192 tokens. Compared to most other open-source models, this model was only trained using open-source relevance-pair datasets with permissive, enterprise-friendly license, plus IBM collected and generated datasets. The r2 models show strong performance across standard and IBM-built information retrieval benchmarks (BEIR, ClapNQ), code retrieval (COIR), long-document search benchmarks (MLDR, LongEmbed), conversational multi-turn… Open weights apache-2.0 48M parameters 8,192 tokens sentence-transformers [View model](https://savrn.com/models/granite-embedding-small-english-r2) Model · Feature extraction ### [bge-small-zh-v1.5](https://savrn.com/models/bge-small-zh-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) More details please refer to our Github: FlagEmbedding. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs. Updates - 10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper:fire: - 09/15/2023: The technical report of BGE has been released - 09/15/2023: The masive training data of BGE has been released - 09/12/2023: New models: - 09/07/2023: Update fine-tune code: Add script to mine hard negatives and support adding instruction during fine-tuning. - 08/09/2023: BGE… Open weights mit 24M parameters 512 tokens transformers [View model](https://savrn.com/models/bge-small-zh-v1-5) Model · Feature extraction ### [bge-base-en](https://savrn.com/models/bge-base-en) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) Recommend switching to newest BAAI/bge-base-en-v1.5, which has more reasonable similarity distribution and same method of usage. More details please refer to our Github: FlagEmbedding. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs. Updates - 10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper:fire: - 09/15/2023: The technical report of BGE has been released - 09/15/2023: The masive training data of BGE has been released - 09/12/2023: New models: - 09/07/2023… Open weights mit 109M parameters 512 tokens transformers [View model](https://savrn.com/models/bge-base-en) Model · Feature extraction ### [mxbai-embed-large-v1](https://savrn.com/models/mxbai-embed-large-v1) [Mixedbread](https://savrn.com/model-publishers/mixedbread-ai) Here, we provide several ways to produce sentence embeddings. Please note that you have to provide the prompt Represent this sentence for searching relevant passages: for query if you want to use it for retrieval. Besides that you don't need any prompt. Our model also supports Matryoshka Representation Learning and binary quantization. Here, we provide several ways to produce sentence embeddings. Please note that you have to provide the prompt Represent this sentence for searching relevant passages: for query if you want to use it for retrieval. Besides that you don't need any prompt. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then… Open weights apache-2.0 335M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/mxbai-embed-large-v1) Model · Feature extraction ### [Qwen3-Embedding-8B](https://savrn.com/models/qwen3-embedding-8b) [Qwen](https://savrn.com/model-publishers/qwen) The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility: The… Open weights apache-2.0 7.6B parameters 40,960 tokens sentence-transformers [View model](https://savrn.com/models/qwen3-embedding-8b) Model · Feature extraction ### [bge-reranker-large](https://savrn.com/models/bge-reranker-large) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) We have updated the new reranker, supporting larger lengths, more languages, and achieving better performance. More details please refer to our Github: FlagEmbedding. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 3/18/2024: Release new rerankers, built upon powerful M3 and LLM (GEMMA and MiniCPM, not so large actually) backbones, supporitng multi-lingual processing and larger inputs, massive improvements of ranking performances on BEIR, C-MTEB/Retrieval, MIRACL, LlamaIndex Evaluation. - 3/18/2024: Release Visualized-BGE, equipping BGE with visual capabilities. Visualized-BGE can be utilized to generate embeddings for hybrid image-text… Open weights mit 560M parameters 514 tokens transformers [View model](https://savrn.com/models/bge-reranker-large) Model · Feature extraction ### [Qwen3-Embedding-4B](https://savrn.com/models/qwen3-embedding-4b) [Qwen](https://savrn.com/model-publishers/qwen) The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility: The… Open weights apache-2.0 4B parameters 40,960 tokens sentence-transformers [View model](https://savrn.com/models/qwen3-embedding-4b) Model · Feature extraction ### [multilingual-e5-large-instruct](https://savrn.com/models/multilingual-e5-large-instruct) [Liang Wang](https://savrn.com/model-publishers/intfloat) Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 24 layers and the embedding size is 1024. Below are examples to encode queries and passages from the MS-MARCO passage ranking dataset. Usage with Infinity: This model is initialized from xlm-roberta-large and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta, but low-resource languages may see performance degradation. First stage: contrastive pre-training with 1 billion weakly supervised text pairs. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. 1. Do I need to add instructions to the query? Yes, this… Open weights mit 560M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/multilingual-e5-large-instruct) Model · Feature extraction ### [jina-embeddings-v3](https://savrn.com/models/jina-embeddings-v3) [Jina AI](https://savrn.com/model-publishers/jinaai) jina-embeddings-v3 is a multilingual multi-task text embedding model designed for a variety of NLP applications. Based on the Jina-XLM-RoBERTa architecture, this model supports Rotary Position Embeddings to handle long input sequences up to 8192 tokens. Additionally, it features 5 LoRA adapters to generate task-specific embeddings efficiently. - retrieval.query: Used for query embeddings in asymmetric retrieval tasks - retrieval.passage: Used for passage embeddings in asymmetric retrieval tasks - separation: Used for embeddings in clustering and re-ranking applications - classification: Used for embeddings in classification tasks - text-matching: Used for embeddings in tasks that quantify… Open weights cc-by-nc-4.0 572M parameters 8,194 tokens transformers [View model](https://savrn.com/models/jina-embeddings-v3) Model · Feature extraction ### [SapBERT-from-PubMedBERT-fulltext](https://savrn.com/models/sapbert-from-pubmedbert-fulltext) [Language Technology Lab @University of Cambridge](https://savrn.com/model-publishers/cambridgeltl) [news] A cross-lingual extension of SapBERT will appear in the main onference of ACL 2021! [news] SapBERT will appear in the conference proceedings of NAACL 2021! SapBERT by Liu et al. (2020). Trained with UMLS 2020AA (English only), using microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext as the base model. The input should be a string of biomedical entity names, e.g., "covid infection" or "Hydroxychloroquine". The [CLS] embedding of the last layer is regarded as the output. The following script converts a list of strings (entity names) into embeddings. For more details about training and eval, see SapBERT github repo. Open weights apache-2.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/sapbert-from-pubmedbert-fulltext) Model · Feature extraction ### [jina-embeddings-v2-small-en](https://savrn.com/models/jina-embeddings-v2-small-en) [Jina AI](https://savrn.com/model-publishers/jinaai) The easiest way to starting using jina-embeddings-v2-small-en is to use Jina AI's Embedding API. jina-embeddings-v2-small-en is an English, monolingual embedding model supporting 8192 sequence length. It is based on a BERT architecture (JinaBERT) that supports the symmetric bidirectional variant of ALiBi to allow longer sequence length. The backbone jina-bert-v2-small-en is pretrained on the C4 dataset. The model is further trained on Jina AI's collection of more than 400 millions of sentence pairs and hard negatives. These pairs were obtained from various domains and were carefully selected through a thorough cleaning process. The embedding model was trained using 512 sequence length, but… Open weights apache-2.0 33M parameters 8,192 tokens sentence-transformers [View model](https://savrn.com/models/jina-embeddings-v2-small-en) Model · Feature extraction ### [bge-large-zh-v1.5](https://savrn.com/models/bge-large-zh-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) For more details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical… Open weights mit 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-large-zh-v1-5) Model · Feature extraction ### [wavlm-large](https://savrn.com/models/wavlm-large) [Microsoft](https://savrn.com/model-publishers/microsoft) The large model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. Note: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin… Open weights transformers [View model](https://savrn.com/models/wavlm-large) Model · Feature extraction ### [w2v-bert-2.0](https://savrn.com/models/w2v-bert-2-0) [AI at Meta](https://savrn.com/model-publishers/facebook) We are open-sourcing our Conformer-based W2v-BERT 2.0 speech encoder as described in Section 3.2.1 of the paper, which is at the core of our Seamless models. This model was pre-trained on 4.5M hours of unlabeled audio data covering more than 143 languages. It requires finetuning to be used for downstream tasks such as Automatic Speech Recognition (ASR), or Audio Classification. This model and its training are supported by Transformers, more on it in the docs. This is a bare checkpoint without any modeling head, and thus requires finetuning to be used for downstream tasks such as ASR. You can however use it to extract audio embeddings from the top layer with this code snippet: To learn more… Open weights mit 580M parameters transformers [View model](https://savrn.com/models/w2v-bert-2-0) Model · Feature extraction ### [UAE-Large-V1](https://savrn.com/models/uae-large-v1) [WhereIsAI](https://savrn.com/model-publishers/whereisai) WhereIsAI/UAE-Large-V1 is licensed under MIT. Feel free to use it in any scenario. If you use it for academic papers, you could cite us via citation info. Welcome to using AnglE to train and infer powerful sentence embeddings. Achievements - May 16, 2024 | AnglE's paper is accepted by ACL 2024 Main Conference - Dec 4, 2023 | Our universal English sentence embedding WhereIsAI/UAE-Large-V1 achieves SOTA on the MTEB Leaderboard with an average score of 64.64! - WhereIsAI/UAE-Code-Large-V1: This model can be used for code or GitHub issue similarity measurement. There is no need to specify any prompts. For retrieval purposes, please use the prompt Prompts.C for query (not for document). Infinity… Open weights mit 335M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/uae-large-v1) Model · Feature extraction ### [splade-cocondenser-selfdistil](https://savrn.com/models/splade-cocondenser-selfdistil) [NAVER](https://savrn.com/model-publishers/naver) SPLADE model for passage retrieval. For additional details, please visit: This is a SPLADE Sparse Encoder model. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval. First install the Sentence Transformers library: Then you can load this model and run inference. If you use our checkpoint, please cite our work Open weights cc-by-nc-sa-4.0 512 tokens sentence-transformers [View model](https://savrn.com/models/splade-cocondenser-selfdistil) Model · Feature extraction ### [dragon-multiturn-query-encoder](https://savrn.com/models/dragon-multiturn-query-encoder) [NVIDIA](https://savrn.com/model-publishers/nvidia) We introduce Dragon-multiturn, a retriever specifically designed for the conversational QA scenario. It can handle conversational query which combine dialogue history with the current query. It is built on top of the Dragon retriever. The details of Dragon-multiturn can be found in here. Please note that Dragon-multiturn is a dual encoder consisting of a query encoder and a context encoder. This repository is only for the query encoder of Dragon-multiturn for getting the query embeddings, and you also need the context encoder to get context embeddings, which can be found here. Both query encoder and context encoder share the same tokenizer. Retrieval results across five multi-turn QA… Open weights other 512 tokens transformers [View model](https://savrn.com/models/dragon-multiturn-query-encoder) Model · Feature extraction ### [dragon-multiturn-context-encoder](https://savrn.com/models/dragon-multiturn-context-encoder) [NVIDIA](https://savrn.com/model-publishers/nvidia) We introduce Dragon-multiturn, a retriever specifically designed for the conversational QA scenario. It can handle conversational query which combine dialogue history with the current query. It is built on top of the Dragon retriever. The details of Dragon-multiturn can be found in here. Please note that Dragon-multiturn is a dual encoder consisting of a query encoder and a context encoder. This repository is only for the context encoder of Dragon-multiturn for getting the context embeddings, and you also need the query encoder to get query embeddings, which can be found here. Both query encoder and context encoder share the same tokenizer. Retrieval results across five multi-turn QA… Open weights other 512 tokens transformers [View model](https://savrn.com/models/dragon-multiturn-context-encoder) Model · Feature extraction ### [clap-htsat-unfused](https://savrn.com/models/clap-htsat-unfused) [LAION eV](https://savrn.com/model-publishers/laion) The abstract of the paper states that: You can use this model for zero shot audio classification or extracting audio and/or textual features. You can also get the audio and text embeddings using ClapModel If you are using this model for your work, please consider citing the original paper Open weights apache-2.0 514 tokens transformers [View model](https://savrn.com/models/clap-htsat-unfused) Model · Feature extraction ### [jina-embeddings-v5-omni-small](https://savrn.com/models/jina-embeddings-v5-omni-small) [Jina AI](https://savrn.com/model-publishers/jinaai) Average score vs. parameter count across image (MIEB-Lite), video (MMEB-V), and audio (MAEB) benchmarks — jina-v5-omni-nano and jina-v5-omni-small define the open-weight frontier (Table 1 in the ArXiv report). jina-embeddings-v5-omni-small is a multimodal embedding model that accepts text, images, video, and audio and produces embeddings in a shared vector space aligned with the text-only jinaai/jina-embeddings-v5-text-small — so you can index with text and query with any modality, no reindexing. For a more compact alternative, see jinaai/jina-embeddings-v5-omni-nano. This is the base repository — it holds all task adapters (retrieval, classification, clustering, text-matching). For a… Open weights cc-by-nc-4.0 1.6B parameters 32,768 tokens transformers [View model](https://savrn.com/models/jina-embeddings-v5-omni-small) Model · Feature extraction ### [specter2_base](https://savrn.com/models/specter2-base) [Ai2](https://savrn.com/model-publishers/allenai) SPECTER2 is the successor to SPECTER and is capable of generating task specific embeddings for scientific tasks when paired with adapters. This is the base model to be used along with the adapters. Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications. Note:For general embedding purposes, please use allenai/specter2. To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below. Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to… Open weights apache-2.0 512 tokens transformers [View model](https://savrn.com/models/specter2-base) Model · Feature extraction ### [wavlm-base-plus](https://savrn.com/models/wavlm-base-plus) [Microsoft](https://savrn.com/model-publishers/microsoft) The base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. Note: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin… Open weights transformers [View model](https://savrn.com/models/wavlm-base-plus) Model · Feature extraction ### [bge-base-zh-v1.5](https://savrn.com/models/bge-base-zh-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) More details please refer to our Github: FlagEmbedding. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs. Updates - 10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper:fire: - 09/15/2023: The technical report of BGE has been released - 09/15/2023: The masive training data of BGE has been released - 09/12/2023: New models: - 09/07/2023: Update fine-tune code: Add script to mine hard negatives and support adding instruction during fine-tuning. - 08/09/2023: BGE… Open weights mit 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-base-zh-v1-5) Model · Feature extraction ### [Qwen3-Embedding-4B-W4A16-G128](https://savrn.com/models/qwen3-embedding-4b-w4a16-g128) [Mou Geren](https://savrn.com/model-publishers/boboliu) GPTQ Quantized Qwen/Qwen3-Embedding-4B with THUIR/T2Ranking and m-a-p/COIG-CQIA for calibration set. ~0.72% lost in C-MTEB. Evaluation performed with official code. pip install compressed-tensors optimum and auto-gptq / gptqmodel, then goto the official usage guide. Open weights apache-2.0 4.1B parameters 40,960 tokens sentence-transformers [View model](https://savrn.com/models/qwen3-embedding-4b-w4a16-g128) Model · Feature extraction ### [jina-embeddings-v2-base-code](https://savrn.com/models/jina-embeddings-v2-base-code) [Jina AI](https://savrn.com/model-publishers/jinaai) The easiest way to starting using jina-embeddings-v2-base-code is to use Jina AI's Embedding API. jina-embeddings-v2-base-code is an multilingual embedding model speaks English and 30 widely used programming languages. Same as other jina-embeddings-v2 series, it supports 8192 sequence length. jina-embeddings-v2-base-code is based on a Bert architecture (JinaBert) that supports the symmetric bidirectional variant of ALiBi to allow longer sequence length. The backbone jina-bert-v2-base-code is pretrained on the github-code dataset. The model is further trained on Jina AI's collection of more than 150 millions of coding question answer and docstring source code pairs. These pairs were obtained… Open weights apache-2.0 161M parameters 8,192 tokens sentence-transformers [View model](https://savrn.com/models/jina-embeddings-v2-base-code) Model · Feature extraction ### [qwen3.5-4l-vocab40k-en-ko-headless](https://savrn.com/models/qwen3-5-4l-vocab40k-en-ko-headless) [Junsung Kim](https://savrn.com/model-publishers/mp-juuuns) A headless four-layer text backbone distilled from Qwen3.5-0.8B, with a vocabulary cut to English and Korean. It has no language-model head, no classification head, no labels and no thresholds. You attach a head and train it. This card is the record of how it was made. It walks the whole path — prompting the original model, turning it into a classifier, removing layers, changing precision, cutting the vocabulary, and cutting it again by rule — and shows what each step measured. We are not arguing that this model is better than anything. We built it, we measured it beside other models, and where we have a guess about why a number moved we say it is a guess. Every arm below was trained… Open weights apache-2.0 121M parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-5-4l-vocab40k-en-ko-headless) Model · Feature extraction ### [jano-tts](https://savrn.com/models/jano-tts) [Jano](https://savrn.com/model-publishers/jano3) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 25M parameters transformers [View model](https://savrn.com/models/jano-tts) Model · Feature extraction ### [MicroGlot](https://savrn.com/models/microglot) [Athan Zhaohong Li](https://savrn.com/model-publishers/athanzli) A taxonomy-informed sparse DNA foundation model for microbial genomics. MicroGlot is a 23-layer decoder-only mixture-of-experts transformer pretrained on 378.3 billion nucleotides from 3.70 million sequences across 99,700 microbial species, spanning bacteria, archaea, fungi, protists, viruses and plasmids. It encodes the taxonomic hierarchy as hyperbolic (Poincaré) embeddings and uses them both as an input token and to steer expert routing. Paper: A Taxonomy-Informed Sparse DNA Foundation Model for Microbial Genomics\ A species is known if it is one of the 99,700 pretraining species (check with tokenizer.hasspecies(name)). For taxonomic classification tasks, use MicroGlot-plain, as… Open weights cc-by-4.0 3B parameters transformers [View model](https://savrn.com/models/microglot) Model · Feature extraction ### [Sovereign-Swarm-Coherence-v1](https://savrn.com/models/sovereign-swarm-coherence-v1) [Alfredo Medina](https://savrn.com/model-publishers/itsnotailabs) The Sovereign-Swarm-Coherence-v1 is a production-verified PyTorch Multi-Head Self-Attention Transformer model designed for Robotics & Micro-Drone Swarm Control. Unlike generic models with arbitrary weight reporting, this repository explicitly itemizes learned trainable parameters versus non-trainable positional encoding constants: - Trainable Learned Parameters (requiresgrad=True): 800,019 - Positional Encoding Constant Buffer Elements (posencoder.pe): 640,000 $$R = \left| \frac{1}{N} \sum{j=1}^{N} e^{i \thetaj} \right|$$ - Computes exact Kuramoto phase order parameter R and 2D Euclidean pairwise collision risk geometry for micro-drone swarms. Apache 2.0 License © ItsNotAI LABS Open weights apache-2.0 1M parameters [View model](https://savrn.com/models/sovereign-swarm-coherence-v1) Model · Feature extraction ### [tiny-audio-granite-qwen](https://savrn.com/models/tiny-audio-granite-qwen) [Alex Kroman](https://savrn.com/model-publishers/mazesmazes) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 1.9B parameters transformers [View model](https://savrn.com/models/tiny-audio-granite-qwen) Model · Feature extraction ### [Vela-1.0-Omni-Nano](https://savrn.com/models/vela-1-0-omni-nano) [vLLM Semantic Router](https://savrn.com/model-publishers/llm-semantic-router) Text, images, speech and environmental audio in one embedding space. Vela Omni Nano supports multimodal search, routing and clustering with normalized vectors that can be compared directly. A frozen CLAP audio branch adds environmental-sound information to the existing speech representation. Text and image computations are retained; audio embeddings are newly trained and evaluated. Architecture and measured identity. Scores are 0–100; higher is better. The comparison uses the same held-out evaluation examples, complete retrieval pools and 128-token text cap for both models. Bold marks improvement over the original small model. These known test pools are reused across releases. The common… Open weights apache-2.0 164M parameters pytorch [View model](https://savrn.com/models/vela-1-0-omni-nano) Model · Feature extraction ### [Vela-1.0-Omni-Mini](https://savrn.com/models/vela-1-0-omni-mini) [vLLM Semantic Router](https://savrn.com/model-publishers/llm-semantic-router) Text, images, speech and environmental sounds in one embedding space. Vela Omni Mini supports multimodal search, routing and clustering with normalized vectors that can be compared directly. Scores are 0–100; higher is better. The comparison uses the same held-out evaluation examples, complete retrieval pools and 128-token text cap for both models. Bold marks improvement over the original large model. These known test pools are reused across releases. The common protocol uses labeled TRAIN prototypes for text classification and all matching positives for retrieval; it is separate from official MTEB classification. All 14 metrics, Macro-F1, exact counts and uncertainty. The primary metric… Open weights apache-2.0 1.4B parameters pytorch [View model](https://savrn.com/models/vela-1-0-omni-mini) Model · Feature extraction ### [vit_giant_patch14_224.dinobloom](https://savrn.com/models/vit-giant-patch14-224-dinobloom) [Laureηt Fainsin](https://savrn.com/model-publishers/1aurent) Model Type: Feature backbone; Params: 1136M (giant); Image size: 224 x 224 x 3; Patch size: 14 x 14 x 3; Repository: github.com:marrlab/DinoBloom; Original Weights: Zenodo. Open weights apache-2.0 1.1B parameters timm [View model](https://savrn.com/models/vit-giant-patch14-224-dinobloom) Model · Feature extraction ### [tiny-audio-granite-qwen-frozen-4](https://savrn.com/models/tiny-audio-granite-qwen-frozen-4) [Alex Kroman](https://savrn.com/model-publishers/mazesmazes) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 13M parameters transformers [View model](https://savrn.com/models/tiny-audio-granite-qwen-frozen-4) Model · Feature extraction ### [meta-encoder](https://savrn.com/models/meta-encoder) [AI at Meta](https://savrn.com/model-publishers/facebook) Multimodal System One Encoder with a natural language interface for instruction-following encoding: give it a task and a list of candidates, and it scores the candidates by task specification. Both a task and each candidate are expressed in natural language — instructions, queries, questions, state descriptions, criteria — with image and video as side information. - Natural language interface. No rigid schemas. Describe the task and the candidates in free-form text. - Highly-efficient cacheable representations. Candidates and task are encoded separately by prompt instructions that ground each other. - Scales to arbitrarily large candidate sets. Matching is an inner product over… Access requested at publisher apache-2.0 29.8B parameters transformers [View model](https://savrn.com/models/meta-encoder) Model · Feature extraction ### [all-MiniLM-L6-v2](https://savrn.com/models/all-minilm-l6-v2-2) [Joshua](https://savrn.com/model-publishers/xenova) https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then use the model to compute embeddings like this: You can convert this Tensor to a nested JavaScript array using.tolist(): Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx). Open weights apache-2.0 512 tokens transformers.js [View model](https://savrn.com/models/all-minilm-l6-v2-2) Model · Feature extraction ### [bge-base-en-v1.5](https://savrn.com/models/bge-base-en-v1-5-2) [Joshua](https://savrn.com/model-publishers/xenova) https://huggingface.co/BAAI/bge-base-en-v1.5 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then use the model to compute embeddings, as follows: You can also use the model for retrieval. For example: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx). Open weights mit 512 tokens transformers.js [View model](https://savrn.com/models/bge-base-en-v1-5-2) Model · Feature extraction ### [1](https://savrn.com/models/1) [Unsloth Backup Account](https://savrn.com/model-publishers/unslothai) Open weights 2,048 tokens transformers [View model](https://savrn.com/models/1) Model · Feature extraction ### [e5-mistral-7b-instruct-bnb-4bit](https://savrn.com/models/e5-mistral-7b-instruct-bnb-4bit) [Gábor Hosu](https://savrn.com/model-publishers/gabor-hosu) This model is a quantized version of the original model intfloat/e5-mistral-7b-instruct. It's quantized using the BitsAndBytes library to 4-bit using the bnb-my-repo space. - bnb4bitquanttype: nf4 - bnb4bitusedoublequant: True - bnb4bitcomputedtype: bfloat16 - bnb4bitquantstorage: uint8 Improving Text Embeddings with Large Language Models. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 32 layers and the embedding size is 4096. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Have a look at configsentencetransformers.json for the prompts that are pre-configured, such as websearchquery… Open weights mit 7.3B parameters 32,768 tokens sentence-transformers [View model](https://savrn.com/models/e5-mistral-7b-instruct-bnb-4bit) Model · Feature extraction ### [repeat](https://savrn.com/models/repeat) [Unsloth Backup Account](https://savrn.com/model-publishers/unslothai) Open weights transformers [View model](https://savrn.com/models/repeat) Model · Feature extraction ### [conv-bert-base](https://savrn.com/models/conv-bert-base) [YITU Technology](https://savrn.com/model-publishers/yitutech) Open weights 512 tokens transformers [View model](https://savrn.com/models/conv-bert-base) Model · Feature extraction ### [SheetSage2-GGUF](https://savrn.com/models/sheetsage2-gguf) [Audio.cpp](https://savrn.com/model-publishers/audio-cpp) GGUF conversion of m-a-p/SheetSage2 for audio.cpp. SheetSage2 transcribes music into melody, chords, beats, key, structure, and editable scores. This is a converted checkpoint, not a new model or an official upstream release. The packaged file uses the audio.cpp SheetSage2 runtime, not the upstream Transformers loader. The upstream model.safetensors is only 228,738,564 bytes (228.74 MB): it contains SheetSage2 adapters and task-specific weights and relies on the separately downloaded MERT-v2-FullSong backbone. The GGUF includes that backbone with the LoRA updates already merged, plus the task weights and embedded configuration. No separate backbone checkpoint is needed at inference time.… Open weights cc-by-nc-4.0 transformers [View model](https://savrn.com/models/sheetsage2-gguf) Model · Feature extraction ### [SheetSage2](https://savrn.com/models/sheetsage2) [Multimodal Art Projection](https://savrn.com/model-publishers/m-a-p) SheetSage2 turns music recordings into lead sheets and timed musical annotations. Transcribe a complete song, edit its ABC or MIDI, render a piano preview, or extract embeddings and token predictions for your own tools. Built on MERT-v2-FullSong, with adapters that merge automatically when you load the model. 2026-09-21: Fixed missing enharmonic spelling correction for key and chord labels. Chord spelling now follows the local key. This updates key/chord labels and ABC notation without changing musical pitches or timing. If you downloaded the repository or model before this update (2026-09-21), please update to the latest repository code. Model weights are unchanged. Use Python 3.10 or 3.11… Open weights cc-by-nc-4.0 57M parameters transformers [View model](https://savrn.com/models/sheetsage2) Model · Feature extraction ### [Qwen3-Voice-Embedding-12Hz-1.7B](https://savrn.com/models/qwen3-voice-embedding-12hz-1-7b) [Markus](https://savrn.com/model-publishers/marksverdhei) Standalone ECAPA-TDNN voice encoder extracted from Qwen/Qwen3-TTS-12Hz-1.7B-Base. Produces 2048-dimensional x-vector speaker embeddings from audio. The encoder follows the ECAPA-TDNN architecture (Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification) and uses Res2Net blocks, squeeze-excitation attention, and attentive statistical pooling. Speaker embeddings can be stored and shared as SafeTensors files. These embeddings are designed to drive voice cloning in the Qwen3-TTS family. There are two main inference paths: the qwentts Python package and the vLLM-Omni serving API. The qwentts package wraps the TTS model and exposes generatevoiceclone. To… Open weights apache-2.0 12M parameters transformers [View model](https://savrn.com/models/qwen3-voice-embedding-12hz-1-7b) Model · Feature extraction ### [starwell](https://savrn.com/models/starwell) [Charles Norton](https://savrn.com/model-publishers/phanerozoic) Starwell is a generative model for stellarator design. Given a number of field periods, an aspect ratio and a target magnetic-gradient scale length LgradB, it samples a plasma boundary for the mhdstable problem of the ConStellaration benchmark, predicts its benchmark metrics, and lays out modular coils for it. Boundaries are SurfaceRZFourier dicts (rcos, zsin) that constellaration evaluates directly; sample also takes tau, guidance, steps and seed, and model.config.sampling holds the integrator's defaults. Coils are simsopt CurveXYZFourier coefficients for one half period with their currents, and simsopt.field.coilsviasymmetries builds the full set; limits (in metres and per metre) sets the… Open weights mit 26M parameters transformers [View model](https://savrn.com/models/starwell) Model · Feature extraction ### [univ_conformer_small_ge2e](https://savrn.com/models/univ-conformer-small-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 2M parameters flaxspeaker [View model](https://savrn.com/models/univ-conformer-small-ge2e) Model · Feature extraction ### [univ_lstm_small_ge2e](https://savrn.com/models/univ-lstm-small-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 2M parameters flaxspeaker [View model](https://savrn.com/models/univ-lstm-small-ge2e) Model · Feature extraction ### [univ_ecapa_tdnn_small_ge2e](https://savrn.com/models/univ-ecapa-tdnn-small-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 2M parameters flaxspeaker [View model](https://savrn.com/models/univ-ecapa-tdnn-small-ge2e) Model · Feature extraction ### [ls_lstm_small_ge2e](https://savrn.com/models/ls-lstm-small-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 2M parameters flaxspeaker [View model](https://savrn.com/models/ls-lstm-small-ge2e) Model · Feature extraction ### [social-jev-0.6B-preview](https://savrn.com/models/social-jev-0-6b-preview) [Social Jev](https://savrn.com/model-publishers/social-jev) SocialJev is a family of classification foundation models for the social sciences, inspired by TypeSafe’s Jev. The models combine the flexibility of modern language models pretrained on trillions of tokens of text with the speed of lightweight NLP methods. Define your task through a simple typed interface and SocialJev returns typed outputs. Note: SocialJev is under active development. Interfaces may change between early releases. The model can be used directly through Transformers without installing the SocialJev package: Results are ordered first by document, then by query for that document. Each result provides.choice and.probabilities; the probabilities above are illustrative. The… Open weights 596M parameters transformers [View model](https://savrn.com/models/social-jev-0-6b-preview) Model · Feature extraction ### [univ_transformer_small_ge2e](https://savrn.com/models/univ-transformer-small-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 1M parameters flaxspeaker [View model](https://savrn.com/models/univ-transformer-small-ge2e) Model · Feature extraction ### [univ_conformer_tiny_ge2e](https://savrn.com/models/univ-conformer-tiny-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 693,124 parameters flaxspeaker [View model](https://savrn.com/models/univ-conformer-tiny-ge2e) Model · Feature extraction ### [univ_ecapa_tdnn_base_ge2e](https://savrn.com/models/univ-ecapa-tdnn-base-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 3M parameters flaxspeaker [View model](https://savrn.com/models/univ-ecapa-tdnn-base-ge2e) Model · Feature extraction ### [univ_ecapa_tdnn_tiny_ge2e](https://savrn.com/models/univ-ecapa-tdnn-tiny-ge2e) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with fixed 180-frame (1.8 s) crops and all-ones validity masks, not with the U(90, 180) variable-length crops that are the current pipeline default: the training code in use at the time defaulted the batchers to… Open weights apache-2.0 626,720 parameters flaxspeaker [View model](https://savrn.com/models/univ-ecapa-tdnn-tiny-ge2e) Model · Feature extraction ### [univ_conformer_small_ge2e_contrast](https://savrn.com/models/univ-conformer-small-ge2e-contrast) [Quan](https://savrn.com/model-publishers/wq2012) This model was trained for 400 gradient steps with mini-batches of 32 utterances (8 speakers x 4 utterances), i.e. about 1.35 epochs over the 9,447-utterance universal corpus, on a CPU workstation, with a single seed (42). Losses are not converged at this budget. All EERs below are therefore far from state of the art and are only meaningful for relative comparisons between FlaxSpeaker checkpoints trained under the same budget. Training-crop provenance. This checkpoint was trained with U(90, 180)-frame variable-length crops and an exact validity mask (the current pipeline default); the shipped config.json / YAML (variablelengthtraining: true) describes the released weights. Step-0 loss… Open weights apache-2.0 2M parameters flaxspeaker [View model](https://savrn.com/models/univ-conformer-small-ge2e-contrast) ## Questions ### Which Feature extraction models are most downloaded? By monthly downloads reported by the Hugging Face Hub: bge-small-en-v1.5 (55.4M); bge-large-en-v1.5 (9.8M); bge-base-en-v1.5 (8.8M). ## Other Tasks - [Text Generation](https://savrn.com/models/tasks/text-generation) 1548 - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 577 - [Robotics](https://savrn.com/models/tasks/robotics) 398 - [Text Classification](https://savrn.com/models/tasks/text-classification) 331 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 232 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 187 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 145 - [Image Classification](https://savrn.com/models/tasks/image-classification) 139 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 100 - [Token Classification](https://savrn.com/models/tasks/token-classification) 100 [See all](https://savrn.com/models/tasks)