source languages: pl; target languages: en; OPUS readme: pl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
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.
Model · Zero-shot classification
deberta-v3-large-zeroshot-v1
The model is designed for zero-shot classification with the Hugging Face pipeline. The model should be substantially better at zero-shot classification than my other zero-shot models on the The model can do one universal task: determine whether a hypothesis is true or nottrue given a text (also called entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is so universal that any classification task can be reformulated into the task. The model was trained on a mixture of 27 tasks and 310 classes that have been reformatted into this universal format. 1. 26 classification tasks with ~400k texts: 'amazonpolarity', 'imdb', 'appreviews'…
It has been finetuned for 3 epochs on SQuAD2.0. DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data. In DeBERTa V3, we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our paper. Please check the official repository for more implementation details and updates. mDeBERTa is multilingual version of DeBERTa…
Fine-tuned Vietnamese Kokoro TTS artifacts. - kokorovi.pth: PyTorch Kokoro KModel checkpoint for inference. - kokorovi.onnx: ONNX Runtime export of the acoustic model. - kokorovivoicepack.pt: default Vietnamese voicepack. - config.json: Kokoro config/vocab used by both PyTorch and ONNX inference. - voicepacks/.pt: additional Vietnamese voicepacks. The ONNX CLI downloads kokorovi.onnx, kokorovivoicepack.pt, and config.json from this repository when local paths are not provided. Install onnxruntime-gpu and pass --device cuda to use CUDAExecutionProvider when available. Vietnamese G2P is handled by vig2p, matching the GitHub inference and training code.
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…
hfname: fin-eng - sourcelanguages: fin - targetlanguages: eng - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fin-eng/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'fin'} - tgtconstituents: {'eng'} - srcmultilingual: False - tgtmultilingual: False - urlmodel: https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.zip - urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.test.txt - srcalpha3: fin - tgtalpha3: eng - shortpair: fi-en - chrF2score: 0.6970000000000001 - brevitypenalty: 0.99 - reflen: 74651.0 - srcname: Finnish - tgtname: English - traindate: 2020-08-05 - srcalpha2: fi…
Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. Evaluated on the SQuAD 2.0 dev set with the official eval script. "exact": 33.67279167589108 "total": 4517 "exact": 48.739495798319325 "total": 1190 Timo Möller: timo.moeller [at] deepset.ai deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to…
This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on | CaseBook(Audio, Omni Full-Duplex) MiniCPM-o 4.5 is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip2, Whisper-medium, CosyVoice2, and Qwen3-8B with a total of 9B parameters. It exhibits a significant performance improvement, and introduces new features for full-duplex multimodal live streaming. Notable features of MiniCPM-o 4.5 include: - Leading Visual Capability. MiniCPM-o 4.5 achieves an average score of 77.6 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 9B parameters, it surpasses widely…
source languages: ja; target languages: en; OPUS readme: ja-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
ComfyUI-key repackaging of the official 8-step PDD acceleration LoRAs for MiniMax-H3 — full audio+video generation in 8 (or 4) sampler steps, CFG-free. These are not plain LoRAs. Each file carries a rank-64 trunk LoRA plus a Parallel Decoding Distillation head bank (32 per-interval final-layer projections per modality, PDD — arXiv:2607.26004). Loading them requires the (also loads the original alibaba-pai files directly — this repo just saves you the in-memory conversion and gives you inspectable standard LoRA keys). Put the LoRA files in ComfyUI/models/pddacc/. Pair FL2VA with an fl2va UNET, Ref2VA with ref2va (bf16 or int8-convrot builds both work). The baked checkpoint goes in…
MOMENT is a family of foundation models for general-purpose time-series analysis. The models in this family (1) serve as a building block for diverse time-series analysis tasks (e.g., forecasting, classification, anomaly detection, and imputation, etc.), (2) are effective out-of-the-box, i.e., with no (or few) task-specific exemplars (enabling e.g., zero-shot forecasting, few-shot classification, etc.), and (3) are tunable using in-distribution and task-specific data to improve performance. For details on MOMENT models, training data, and experimental results, please refer to the paper MOMENT: A Family of Open Time-series Foundation Models. Recommended Python Version: Python 3.11 (support…
Nanonets-OCR2: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging Nanonets-OCR2 by Nanonets is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction. It transforms documents into structured markdown with intelligent content recognition and semantic tagging, making it ideal for downstream processing by Large Language Models (LLMs). Nanonets-OCR2 is packed with features designed to handle complex documents with ease: 1. Start the vLLM server. Check out Docstrange for more details. 1. Increasing the image resolution will improve model's performance. 2. For complex…
This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-base). The Moirai-1.1-R model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with…
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. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…
This repository provides all the necessary tools to perform emotion recognition with a fine-tuned wav2vec2 (base) model using SpeechBrain. It is trained on IEMOCAP training data. For a better experience, we encourage you to learn more about SpeechBrain. The model performance on IEMOCAP test set is: This system is composed of an wav2vec2 model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings. The system is trained with recordings sampled at 16kHz (single channel). The code will…
The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance. This model was contributed by @jadechoghari with the help of @cyrilvallez and @qubvel-hf This is RT-DETRv2 consistently outperforms its predecessor across all…
AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data by Fu-Yun Wang et al. For more details, please refer to our [paper] | [code] | [proj-page] | [civitai].
source languages: bg; target languages: en; OPUS readme: bg-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
GGUF weights for omnivoice.cpp, a C++17/GGML port of OmniVoice (k2-fsa/OmniVoice). Multilingual zero shot TTS, 646 languages, 24 kHz mono. Runs on CPU, CUDA, ROCm, Metal, Vulkan. omnivoice-base-{variant}.gguf Qwen3 0.6B backbone, text -> tokens omnivoice-tokenizer-{variant}.gguf HuBERT + DAC + RVQ, tokens 24 kHz audio Set GGMLBACKEND to force a device, otherwise the runtime picks the best one available. Tokenizer GGUFs are not uniform quants. Three categories get a Same fallback as llama.cpp tensortypefallback: F16 has no block size and matches the runtime target dtype on every backend. The base LM (Qwen3 0.6B, hidden = 1024) has all dimensions divisible by 256 so the fallback never…
SegFormer model fine-tuned on CityScapes at resolution 1024x1024. 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…
Mask2Former model trained on COCO instance segmentation (small-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i)…
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation model, HY-MT1.5-7B. Both models focus on supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations. Among them, HY-MT1.5-7B is an upgraded version of our WMT25 championship model, optimized for explanatory translation and mixed-language scenarios, with newly added support for terminology intervention, contextual translation, and formatted translation. Despite having less than one-third the parameters of HY-MT1.5-7B, HY-MT1.5-1.8B delivers translation performance comparable to its larger counterpart, achieving both high speed and high quality.…
Free ComfyUI workflows, Runpod templates, and guides: https://discord.gg/ZVWVhT43GW https://get.runpod.io/minimax-template A mirror of the MiniMax-H3 LoRAs published on CivitAI. CivitAI-matched files have identical SHA-256 checksums (listed below); the HMMisDogV2 exception is noted in the recent uploads table. CivitAI carries the sample videos, the version history and the comment threads; this repository exists so the weights can be pulled with a plain resolve URL, without an account. One anatomy adapter teaches H3 what a body part looks like. One action adapter teaches it what a body does. They are single-concept and they stack, so put them under whatever character or scene LoRA you are…
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.