Feature Extraction Models

Model · Feature extraction

bge-small-en-v1.5

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

bge-large-en-v1.5

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

bge-base-en-v1.5

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

Qwen3-Embedding-0.6B

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…

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…

Model · Feature extraction

granite-embedding-small-english-r2

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…

Model · Feature extraction

bge-small-zh-v1.5

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

bge-base-en

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

bge-reranker-large

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

Qwen3-Embedding-8B

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…

Model · Feature extraction

mxbai-embed-large-v1

Mixedbread

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…

Model · Feature extraction

jina-embeddings-v3

Jina AI

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…

Model · Feature extraction

Qwen3-Embedding-4B

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…

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…

Model · Feature extraction

SapBERT-from-PubMedBERT-fulltext

Language Technology Lab @University of Cambridge

[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.

Model · Feature extraction

jina-embeddings-v2-small-en

Jina AI

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…

Model · Feature extraction

w2v-bert-2.0

AI at Meta

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…

Model · Feature extraction

bge-large-zh-v1.5

Beijing Academy of Artificial Intelligence

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…

Model · Feature extraction

wavlm-large

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…

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…

Model · Feature extraction

clap-htsat-unfused

LAION eV

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

Model · Feature extraction

splade-cocondenser-selfdistil

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

Model · Feature extraction

dragon-multiturn-query-encoder

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…

Model · Feature extraction

dragon-multiturn-context-encoder

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…

Model · Feature extraction

specter2_base

Ai2

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…

Model · Feature extraction

wavlm-base-plus

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…

Model · Feature extraction

bge-base-zh-v1.5

Beijing Academy of Artificial Intelligence

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…

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.

Model · Feature extraction

jina-embeddings-v2-base-code

Jina AI

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…

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…

Model · Feature extraction

jano-tts

Jano

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).

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…

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

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).

Model · Feature extraction

Vela-1.0-Omni-Nano

vLLM 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…

Model · Feature extraction

Vela-1.0-Omni-Mini

vLLM 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…

Model · Feature extraction

vit_giant_patch14_224.dinobloom

Laureηt Fainsin

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.

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).

Model · Feature extraction

meta-encoder

AI at Meta

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…

Model · Feature extraction

all-MiniLM-L6-v2

Joshua

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).

Model · Feature extraction

bge-base-en-v1.5

Joshua

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).

Model · Feature extraction

jina-embeddings-v5-omni-small

Jina AI

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…

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…

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.…

Model · Feature extraction

SheetSage2

Multimodal Art Projection

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…

Model · Feature extraction

Qwen3-Voice-Embedding-12Hz-1.7B

Markus

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…

Model · Feature extraction

starwell

Charles Norton

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…

CLIP helps researchers find images using written descriptions. It can also compare pictures with one another, or compare text and images in the same collection. A researcher working with historical photographs or newsreel frames could search for descriptions such as “a crowd in a public square” and inspect the closest matches. Choose CLIP when searching images with words matters; an image-only model such as DINO is another option for exploring visual similarity without text. These are possible research uses, not claims that this EIDORA package has been evaluated on historical collections. CLIP was trained largely on internet images and English-language text. It may miss details in…

Model · Feature extraction

Corpus-ViT

Gugu8

A vision encoder with a runtime-selectable token budget, built to sit between an image and an LLM. A coarse 32px grid covers the whole image; a router spends extra 16px detail only on the regions that need it. Output length is 49 + 3k tokens — 49 at k=0, 121 at k=24 — so you choose the tokens/fidelity trade-off per image, at inference, with no retraining. 24.94M parameters. Trained in 6000 steps (~30 min) on 2× Kaggle T4 by distillation from google/siglip-base-patch16-224 (86M). This is a working, honest baseline, not a competitive encoder. On the Flickr30k official test split it reaches 8.95 mean R@1 against the teacher's 83.25 — roughly 10% of its teacher. Chance on 1000 images is 0.10.…

本仓库提供由 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct - 模型显示名称：RK182X-EMBEDDING-gme-Qwen2-VL-2B-Instruct - 源模型：Alibaba-NLP/gme-Qwen2-VL-2B-Instruct - 模型类型：EMBEDDING ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 用于图文检索，输出 embedding 向量。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 Qwen/Qwen3-Embedding-0.6B 转换得到的 RKNN EMBEDDING 模型。 - Model ID：RKNNAI/RK182X-EMBEDDING-Qwen3-Embedding-0.6B - 模型显示名称：RK182X-EMBEDDING-Qwen3-Embedding-0.6B - 源模型：Qwen/Qwen3-Embedding-0.6B - 模型类型：EMBEDDING ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

Model · Feature extraction

CLM-v0.1-8B-MLX

Zhu Lin

The encoder half of Contrastive-LM/CLM-v0.1-8B, quantised for MLX on Apple Silicon. One repository per bit width, matching mlx-community. Each has the weights at the repo root, so the Hub file browser lists every file with its size and mlxlm.load(" ") works. Agreement against a bf16 MLX reference of the same encoder in the same runtime, over 23,926 scored System One questions, through the real head stack (argmax(scale · cos), scale = 100.0 — cosine error is amplified 100×). Pass line. top-1 >= 1.0000 — the measured bf16-vs-bf16 noise floor of this corpus in this runtime — and top-1 (decisive) >= 0.995, where decisive means the reference's own top-1 led by more than 1 nat. A third condition…

Model · Feature extraction

CLM-v0.1-8B-MLX-6bit

Zhu Lin

This is the 6bit variant. Also available: czl/CLM-v0.1-8B-MLX-4bit, czl/CLM-v0.1-8B-MLX-8bit, and the bf16 reference. The encoder half of Contrastive-LM/CLM-v0.1-8B, quantised for MLX on Apple Silicon. mlxlm is generate-only — it has no embeddings entrypoint, and mlxlm.server routes just /v1/completions, /v1/chat/completions, /v1/models and /health. So clmmlx supplies the pooling pass over mlxlm internals: Qwen3Model.call already returns self.norm(h), the post-final-RMSNorm hidden states, which is what vLLM's pooling runner returns in last-token mode. Agreement against a bf16 MLX reference of the same encoder in the same runtime, over 23,926 scored System One questions, through the real…

Model · Feature extraction

CLM-v0.1-8B-MLX-8bit

Zhu Lin

This is the 8bit variant. Also available: czl/CLM-v0.1-8B-MLX-4bit, czl/CLM-v0.1-8B-MLX-6bit, and the bf16 reference. The encoder half of Contrastive-LM/CLM-v0.1-8B, quantised for MLX on Apple Silicon. mlxlm is generate-only — it has no embeddings entrypoint, and mlxlm.server routes just /v1/completions, /v1/chat/completions, /v1/models and /health. So clmmlx supplies the pooling pass over mlxlm internals: Qwen3Model.call already returns self.norm(h), the post-final-RMSNorm hidden states, which is what vLLM's pooling runner returns in last-token mode. Agreement against a bf16 MLX reference of the same encoder in the same runtime, over 23,926 scored System One questions, through the real…

Model · Feature extraction

continuous-mimi-onnx

MaAI

This is a modified ONNX export of the Mimi audio codec encoder. It bypasses the Residual Vector Quantization (RVQ) to directly output continuous feature representations instead of discrete tokens. This preserves fine-grained acoustic details, making it ideal for downstream tasks like real-time dialogue analysis or speech emotion recognition. This model is a derivative work based on the "Mimi" model. Numbers below are illustrative (desktop CPU, FP32 ONNX vs PyTorch kyutai/mimi, streaming chunk emit=1280 @ 16 kHz, inference.py --compare). Your machine, thread counts, and ORT / PyTorch builds will shift them. Speed — RTF (processing time ÷ real-time audio length per chunk) In repeated 1-second…

Model · Feature extraction

CoVisco-L-14

Ernie Research

CoVisco-L-14 is the Stage 1 vision encoder of the CoVisco pipeline (Codec-Native Vision Encoder with Native Token Compression for Efficient Unified Visual Understanding). It encodes images and videos in a unified way and is trained by SigLIP-style distillation against two teacher branches. This repository releases only the vision-encoder weights in the safe.safetensors format, together with the minimal model code and a self-contained loader. The model is a transformers.PreTrainedModel and is loadable via frompretrained (see below). - 4D RoPE (ropetheta=10000) for spatio-temporal positions - Three projection heads (each LayerNorm + Linear, output L2-normalized): - toimagecaption → 1536-d…

Model · Feature extraction

d1-600m-text2sql

Jirameth

Fine-tuned from LiquidAI/d1-omni-600M to select one of four supplied SQL queries using a schema, question, and conversation history. Your application supplies and executes the queries. On 1,000 synthetic development turns, v1 scored 45.6% versus 24.9% for the unchanged base, a gain of 20.7 percentage points. Both used FP32, complete inputs, original query order, batch size 4, and highest-score selection. The set contains 250 four-turn conversations across 10 synthetic clinical task families excluded from training. Each turn receives a fixed supplied history, independent of earlier predictions. This development set was reused for model selection. Results do not establish independent-test or…