Open-Weight Models

Model · Fill mask

Bio_Discharge_Summary_BERT

Emily Alsentzer

The Publicly Available Clinical BERT Embeddings paper contains four unique clinicalBERT models: initialized with BERT-Base (casedL-12H-768A-12) or BioBERT (BioBERT-Base v1.0 + PubMed 200K + PMC 270K) & trained on either all MIMIC notes or only discharge summaries. This model card describes the Bio+Discharge Summary BERT model, which was initialized from BioBERT & trained on only discharge summaries from MIMIC. The BioDischargeSummaryBERT model was trained on all discharge summaries from MIMIC III, a database containing electronic health records from ICU patients at the Beth Israel Hospital in Boston, MA. For more details on MIMIC, see here. All notes from the NOTEEVENTS table were included…

Model · Translation

opus-mt-de-en

Helsinki-NLP Research Group

source languages: de; target languages: en; OPUS readme: de-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.

Model · Text to speech

VoxCPM2

OpenBMB

VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data. - 30-Language Multilingual — No language tag needed; input text in any supported language directly - Voice Design — Generate a novel voice from a natural-language description alone (gender, age, tone, emotion, pace…); no reference audio required - Controllable Cloning — Clone any voice from a short clip, with optional style guidance to steer emotion, pace, and expression while preserving timbre - Ultimate Cloning — Provide reference audio + its transcript for audio-continuation cloning; every vocal nuance…

Model · Fill mask

mmBERT-base

Center for Language and Speech Processing @ JHU

mmBERT is a modern multilingual encoder that significantly outperforms previous generation models like XLM-R on classification, embedding, and retrieval tasks. Built on the ModernBERT architecture with novel multilingual training innovations, mmBERT demonstrates that low-resource languages can be effectively learned during the decay phase of training. It is also significantly faster than any previous multilingual encoder. mmBERT represents the first significant advancement over XLM-R for massively multilingual encoder models. Key features include: 1. Massive Language Coverage - Trained on over 1800 languages with progressive inclusion strategy 2. Modern Architecture - Built on ModernBERT…

Model · Text classification

RADAR-Vicuna-7B

TrustSafeAI

RADAR-Vicuna-7B is an AI-text detector trained via adversarial learning between the detector and a paraphraser on human-text corpus (OpenWebText) and AI-text corpus generated based on OpenWebText. Users could use this detector to assist them in detecting text generated by large language models. Please note that this detector is trained on AI-text generated by Vicuna-7B-v1.1. As the model only supports non-commercial use, the intended users are not allowed to involve this detector into commercial activities. Please refer to the following guidelines to see how to locally run the downloaded model or use our API service hosted on Huggingface Space. We propose adversarial learning between a…

Model · Translation

opus-mt-ru-en

Helsinki-NLP Research Group

This model can be used for translation and text-to-text generation. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Further details about the dataset for this model can be found in the OPUS readme: ru-en

This is an xlm-roberta fine-tuned to restore punctuation, true-case (capitalize), and detect sentence boundaries (full stops) in 47 languages. If you want to just play with the model, the widget on this page will suffice. To use the model offline, the following snippets show how to use the model both with a wrapper (that I wrote, available from PyPI) and manual usuage (using the ONNX and SentencePiece models in this repo). The easiest way to use this model is to install punctuators: But this is just an ONNX and SentencePiece model, so you may run it as you wish. The input to the punctuators API is a list (batch) of strings. Each string will be punctuated, true-cased, and segmented on…

Model · Translation

t5-large

T5 community

The developers of the Text-To-Text Transfer Transformer (T5) write: T5-Large is the checkpoint with 770 million parameters. The developers write in a blog post that the model: See the blog post and research paper for further details. The model is pre-trained on the Colossal Clean Crawled Corpus (C4), which was developed and released in the context of the same research paper as T5. The model was pre-trained on a on a multi-task mixture of unsupervised (1.) and supervised tasks (2.). Thereby, the following datasets were being used for (1.) and (2.): 1. Datasets used for Unsupervised denoising objective: 2. Datasets used for Supervised text-to-text language modeling objective - CoLA Warstadt…

Model · Text classification

distilbert-imdb

Leandro von Werra

This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset (training notebook is here). It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - numepochs: 1 - Transformers 4.15.0 - Pytorch 1.10.0+cu111 - Datasets 1.17.0 - Tokenizers 0.10.3

Model · Token classification

privacy-filter-multilingual-GGUF

LocalAI-io

GGUF conversion of OpenMed/privacy-filter-multilingual, a multilingual PII token-classification model (a fine-tune of openai/privacy-filter). It labels every token with a BIOES tag over 54 PII categories (217 classes) across 16 languages, so it can be served locally with no Python as the encoder/NER tier of a PII redactor. For the full model description, label space, evaluation, limitations, and citations, see the source model card — this card only covers the GGUF packaging and how to run it. This GGUF uses a custom architecture, openai-privacy-filter, that is not (yet) part of 1. privacy-filter.cpp (recommended) — a small standalone GGML engine for exactly this model family, on stock…

Model

byt5-small

Google

ByT5 is a tokenizer-free version of Google's T5 and generally follows the architecture of MT5. ByT5 was only pre-trained on mC4 excluding any supervised training with an average span-mask of 20 UTF-8 characters. Therefore, this model has to be fine-tuned before it is useable on a downstream task. ByT5 works especially well on noisy text data,e.g., google/byt5-small significantly outperforms mt5-small on TweetQA. Paper: ByT5: Towards a token-free future with pre-trained byte-to-byte models Authors: Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel ByT5 works on raw UTF-8 bytes and can be used without a tokenizer: For batched…

Model · Image segmentation

RMBG-1.4

BRIA AI

RMBG v1.4 is our state-of-the-art background removal model, designed to effectively separate foreground from background in a range of categories and image types. This model has been trained on a carefully selected dataset, which includes: general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use cases powering enterprise content creation at scale. The accuracy, efficiency, and versatility currently rival leading source-available models. It is ideal where content safety, legally licensed datasets, and bias mitigation are paramount. Developed by BRIA AI, RMBG v1.4 is available as a source-available model for non-commercial use. To purchase a…

Model · Text to speech

VibeVoice-Realtime-0.5B

Microsoft

VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in ~300 ms (hardware dependent). ▶ Watch demo video (Launch your own realtime demo via the websocket example in Usage) Although the model is primarily built for English, we found that it still exhibits a certain level of multilingual capability—and even performs reasonably well in some languages. We provide nine…

Model · Fill mask

deberta-v2-large-japanese-char-wwm

Language Media Processing Lab at Kyoto University

This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR. This model is trained with character-level tokenization and whole word masking. You can use this model for masked language modeling as follows: You can also fine-tune this model on downstream tasks. There is no need to tokenize texts in advance, and you can give raw texts to the tokenizer. The texts are tokenized into character-level tokens by sentencepiece. We used the following corpora for pre-training: - Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents) - Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)…

Model · Fill mask

codebert-python

NeuLab @ LTI/CMU

This is a microsoft/codebert-base-mlm model, trained for 1,000,000 steps (with batchsize=32) on Python code from the codeparrot/github-code-clean dataset, on the masked-language-modeling task. It is intended to be used in CodeBERTScore: https://github.com/neulab/code-bert-score, but can be used for any other model or task. If you use this model for research, please cite

Model · Image classification

AI-image-detector

Matthew Maybe

NOTE: Unless you are trying to detect imagery generated using older models such as VQGAN+CLIP, please use the updated version of this detector instead. This model is a proof-of-concept demonstration of using a ViT model to predict whether an artistic image was generated using AI. It was created in October 2022, and as such, the training data did not include any samples generated by Midjourney 5, SDXL, or DALLE-3. It still may be able to correctly identify samples from these more recent models due to being trained on outputs of their predecessors. Furthermore the intended scope of this tool is artistic images; that is to say, it is not a deepfake photo detector, and general computer imagery…

However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy.…

Model · Text to image

animagine-xl-4.0

Cagliostro Labs

Animagine XL 4.0, also stylized as Anim4gine, is the ultimate anime-themed finetuned SDXL model and the latest installment of Animagine XL series. Despite being a continuation, the model was retrained from Stable Diffusion XL 1.0 with a massive dataset of 8.4M diverse anime-style images from various sources with the knowledge cut-off of January 7th 2025 and finetuned for approximately 2650 GPU hours. Similar to the previous version, this model was trained using tag ordering method for the identity and style training. With the release of Animagine XL 4.0 Opt (Optimized), the model has been further refined with an additional dataset, improving stability, anatomy accuracy, noise reduction…

Model · Translation

t5-3b

T5 community

The developers of the Text-To-Text Transfer Transformer (T5) write: T5-3B is the checkpoint with 3 billion parameters. The developers write in a blog post that the model: See the blog post and research paper for further details. The model is pre-trained on the Colossal Clean Crawled Corpus (C4), which was developed and released in the context of the same research paper as T5. The model was pre-trained on a on a multi-task mixture of unsupervised (1.) and supervised tasks (2.). Thereby, the following datasets were being used for (1.) and (2.): 1. Datasets used for Unsupervised denoising objective: 2. Datasets used for Supervised text-to-text language modeling objective - CoLA Warstadt et…

Model · Text generation

vlt5-base-keywords

VoiceLab.ai

Results on demo model (different generation method, one model per language): Keywords generated with vlT5-base-keywords: encoder-decoder architecture, vlT5, keyword generation, scientific articles corpus The biggest advantage is the transferability of the vlT5 model, as it works well on all domains and types of text. The downside is that the text length and the number of keywords are similar to the training data: the text piece of an abstract length generates approximately 3 to 5 keywords. It works both extractive and abstractively. Longer pieces of text must be split into smaller chunks, and then propagated to the model. The model was trained on a POSMAC corpus. Polish Open Science…

Model · Text to image

sd-turbo

Stability AI

SD-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. We release SD-Turbo as a research artifact, and to study small, distilled text-to-image models. For increased quality and prompt understanding, we recommend SDXL-Turbo. Please note: For commercial use, please refer to https://stability.ai/license. SD-Turbo is a distilled version of Stable Diffusion 2.1, trained for real-time synthesis. SD-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high…

Model · Image segmentation

segformer-b0-finetuned-ade-512-512

NVIDIA

SegFormer model fine-tuned on ADE20k at resolution 512x512. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository. Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team. SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a…

Model · Any to any

Qwen2.5-Omni-7B

Qwen

Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. We conducted a comprehensive evaluation of Qwen2.5-Omni, which demonstrates strong performance across all modalities when compared to similarly sized single-modality models and closed-source models like Qwen2.5-VL-7B, Qwen2-Audio, and Gemini-1.5-pro. In tasks requiring the integration of multiple modalities, such as OmniBench, Qwen2.5-Omni achieves state-of-the-art performance. Furthermore, in single-modality tasks, it excels in areas including speech recognition (Common…

Model · Text classification

distilroberta-finetuned-financial-news-sentiment-analysis

Manuel Romero

This model is a fine-tuned version of distilroberta-base on the financialphrasebank dataset. It achieves the following results on the evaluation set: This model is a distilled version of the RoBERTa-base model. It follows the same training procedure as DistilBERT. The code for the distillation process can be found here. The model has 6 layers, 768 dimension and 12 heads, totalizing 82M parameters (compared to 125M parameters for RoBERTa-base). On average DistilRoBERTa is twice as fast as Roberta-base. Polar sentiment dataset of sentences from financial news. The dataset consists of 4840 sentences from English language financial news categorised by sentiment. The dataset is divided by…