This model generates a revised version of inputted text with the goal of containing fewer grammatical errors. It was trained with Happy Transformer using a dataset called JFLEG. Here's a full article on how to train a similar model. pip install happytransformer
SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
2,760Models
859Datasets
254Papers
1,692Publishers
5,040Sourced relationships
Updated 2026-09-18 · How the library is built
2,760 models, sorted by most downloaded.
A DenseNet image classification model. Pretrained on ImageNet-1k in timm by Ross Wightman using RandAugment RA recipe. Related to B recipe in ResNet Strikes Back.
This is an image generation model based on training from Illustrious-xl. It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption. For quality tags, we evaluated image popularity through the following process: - Data normalization based on various sources and ratings. - Application of time-based decay coefficients according to date recency. - Ranking of images within the entire dataset based on this processing. Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years. - Latest Danbooru images up to the training date(for v1.0,it mean approximately before 2024-10-23) - E621 images e621-2024-webp-4Mpixel dataset on…
ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 224x224. It was introduced in the paper ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo et al. and first released in this repository. Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization (GRN) layer to ConvNeXt. ConvNeXt V2 significantly improves the performance of pure ConvNets on various…
A ConvNeXt image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
This model combines the SpeechBrain ECAPA-TDNN speaker embedding model with an SVM classifier to predict speaker gender from audio input. The model was trained and evaluated on the VoxCeleb2, Mozilla Common Voice v10.0, and TIMIT datasets - Mozilla Common Voice v10.0 English validated test set: 92.3% accuracy The model was trained on VoxCeleb2 dataset: - Converted to WAV format, single channel, 16kHz sampling rate, 256 kp/s bitrate - Applied SileroVAD for voice activity detection, taking the first voiced segment You can install the package directly from GitHub: - Model was trained on celebrity voices from YouTube interviews - Performance may vary on different audio qualities or recording…
A MobileNet-V4 image classification model. Trained on ImageNet-1k by Ross Wightman. Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 paper with timm enhancements. NOTE: So far, these are the only known MNV4 weights. Official weights for Tensorflow models are unreleased. - MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
Pretrained weights for ProphetNet. ProphetNet is a new pre-trained language model for sequence-to-sequence learning with a novel self-supervised objective called future n-gram prediction. ProphetNet is able to predict more future tokens with a n-stream decoder. The original implementation is Fairseq version at github repo. This pre-trained model can be fine-tuned on sequence-to-sequence tasks. The model could e.g. be trained on headline generation as follows
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features https://arxiv.org/pdf/2502.14786 The model classifies each image into one of the following content categories: This model is intended for applications such as
A ConvNeXt image classification model. CLIP image tower weights pretrained in OpenCLIP on LAION and fine-tuned on ImageNet-12k followed by ImageNet-1k in timm bby Ross Wightman. Please see related OpenCLIP model cards for more details on pretrain: https://huggingface.co/laion/CLIP-convnextxxlarge-laion2B-s34B-b82K-augreg-soup https://huggingface.co/laion/CLIP-convnextlarged.laion2B-s26B-b102K-augreg https://huggingface.co/laion/CLIP-convnextbasew-laion2B-s13B-b82K-augreg https://huggingface.co/laion/CLIP-convnextbasew320-laionaesthetic-s13B-b82K - Learning Transferable Visual Models From Natural Language Supervision: https://arxiv.org/abs/2103.00020 Explore the dataset and runtime metrics…
Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, both asking and answering questions, and displaying knowledge, empathy and personality appropriately, depending on the situation. We show that large scale models can learn these skills when given appropriate training…
ModernBERT multi-task fine-tuned on tasksource NLI tasks, including MNLI, ANLI, SICK, WANLI, doc-nli, LingNLI, FOLIO, FOL-NLI, LogicNLI, Label-NLI and all datasets in the below table). This is the equivalent of an "instruct" version. The model was trained for 200k steps on an Nvidia A30 GPU. It is very good at reasoning tasks (better than llama 3.1 8B Instruct on ANLI and FOLIO), long context reasoning, sentiment analysis and zero-shot classification with new labels. The following table shows model test accuracy. These are the scores for the same single transformer with different classification heads on top. Further gains can be obtained by fine-tuning on a single-task, e.g. SST, but it…
Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Please note: This model is released under the Stability Community License. Visit Stability AI to learn or contact us for commercial licensing details. - For individuals and organizations with annual revenue above $1M: please contact us to get an Enterprise License. For local or self-hosted use, we recommend ComfyUI for node-based UI inference, or diffusers or GitHub for programmatic use. - Text Encoders： This model was trained on a wide variety of data, including synthetic data and…
A ConvNeXt image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 1024 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 1024 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 1024 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to…
X-CLIP model (base-sized, patch resolution of 32) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. This model was trained using 8 frames per video, at a resolution of 224x224. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully…
thanks feiyuuu for report the problem. When using the default pose line the performance may be unstable, this is because the pose label use more thick line in training to have a better look. This difference can be fix by using the following method: Find the util.py in controlnetaux python package, usually the path is like: /your anaconda3 path/envs/your env name/lib/python3.8/site-packages/controlnetaux/openpose/util.py Replace the drawbodypose function with the following code: Use the code below to get started with the model. HumanArt [https://github.com/IDEA-Research/HumanArt], select 2000 images with ground truth pose annotations to generate images and calculate mAP. We are the SOTA…
The license of the quantized files follows the license of the original model: These files are converted using https://github.com/leejet/stable-diffusion.cpp This model can be used with stable-diffusion.cpp. For setup instructions and usage details, please refer to: To use this model in ComfyUI, first install the following custom node: An example ComfyUI workflow is available here: src="https://huggingface.co/leejet/MiniMax-H3-GGUF/resolve/main/assets/example.mp4" controls muted
Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, both asking and answering questions, and displaying knowledge, empathy and personality appropriately, depending on the situation. We show that large scale models can learn these skills when given appropriate training…
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
A Swin Transformer image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors. Explore the dataset and runtime metrics of this model in timm model results.
LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. Encoding always uses vae/, and LTX2Pipeline decodes with vae/ too. The diffusion decoder is a diffusion model in its…
Splinter-base is the pretrained model discussed in the paper Few-Shot Question Answering by Pretraining Span Selection (at ACL 2021). Its original repository can be found here. The model is case-sensitive. Note: This model doesn't contain the pretrained weights for the QASS layer (see paper for details), and therefore the QASS layer is randomly initialized upon loading it. For the model with those weights, see tau/splinter-base-qass. Splinter is a model that is pretrained in a self-supervised fashion for few-shot question answering. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an…
This repository hosts the kokoro models exported for the library as ExecuTorch.pte programs, ready to run on device. These files are published for the ExecuTorch v1.4.1 runtime. ExecuTorch gives no forward compatibility guarantee, so an older runtime may fail to load them. To use them in React Native ExecuTorch, pass the model constant shipped in the library's model registry to the corresponding task pipeline. See the To load these files in your own ExecuTorch runtime, read the first. Kokoro synthesizes speech in 8 languages here, including fine-tuned Polish and German voices. The synthesizer and duration predictor support input shape dynamism over a range of 1 to 128 tokens. Synthesis…
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.