This repository is a compact, custom PyTorch implementation of ViT for Multitask. The small configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lamb with a step schedule. These are starting…
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.
11,122Models
3,164Datasets
285Papers
6,792Publishers
11,852Sourced relationships
Updated 2026-10-18 · How the library is built
11,122 models, sorted by most downloaded.
This is an experimental ViT codebase for Retrieval. It keeps the nano setup intentionally manageable so architecture changes can be inspected before a full training run. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lamb with a polynomial schedule. These are starting values in the script, not evidence of a completed run. For a…
A small ViT implementation for Retrieval, packaged with an explicit configuration and an initialization checkpoint. The giant variant is a reproducible starting point, not a trained model release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses sgd with a onecycle schedule. These are starting values in the script, not evidence of a…
English | 中文 Community-maintained fork of Nunchaku. Nunchaku is an SVDQuant inference engine for 4-bit diffusion models (paper: SVDQuant). The upstream project has not been actively maintained for a long time. This fork keeps the original capabilities while extending model and quantization support, and distributes prebuilt wheels on Hugging Face. Quantized inference for three additional models. Published wheels cover Linux x8664, Linux aarch64, and Windows, all built for CUDA 13.0: - Linux x8664: Python 3.11 + PyTorch 2.11; Python 3.11 / 3.12 / 3.13 + PyTorch 2.14 File names are listed under Prebuilt Wheels. Anima checkpoints store plain INT8. frompretrained(..., device="cuda") packs them…
VIYA reads Vietnamese text and returns typed decisions with calibrated confidence in a single forward pass. It does not generate text: you describe the question and the options in plain language, and VIYA scores every option. Options are free text, so you can add or rename them without retraining. - Vietnamese fact-checking. 87.6 macro-F1 on ViFactCheck with gold evidence (human: 84.9). When it has to find the evidence itself in the full article, it scores 78.7, ahead of Gemini 1.5 Flash, XLM-R large and Mistral 7B. - Full fact-checking pipeline. On ViWikiFC, VIYA finds the right evidence sentence and reaches the right verdict 75.7% of the time; the best published pipeline reaches 67.0%.…
Checkpoints of the two external baselines trained against V4 in the VLA-HAND project. Both were trained and tested on the same three domains (GigaHands, OakInk2, TACO), splits, normalisation statistics and test protocol as V4. Each is the checkpoint with the lowest validation loss, the one all reported test numbers come from. Test split, the first 8 control steps of each test window, three domains pooled. Wrist translation in cm, wrist rotation in degrees (geodesic), fingers in cm; lower is better. VITRA predicts joint angles, so its finger error is measured after MANO forward kinematics and includes an FK floor that SmolVLA does not have. The finger columns are not directly comparable.…
Adapted checkpoints for the EgoTouch Table 1 protocol. The model folder follows the layout used by MIT-Media-Lab/vla-hand-baselines.
A small non-autoregressive yes/no visual question answering model built for research on calibrated decisions. It answers a yes/no question about an image in one forward pass, with no generation and no verbalised confidence. The confidence is the softmax over two token logits followed by a single post-hoc temperature. - Image. A frozen SigLIP2-base encodes the image into its pooled vector (pooleroutput, 768-d). - Prefix token. That vector becomes one prefix token, prepended to the input embeddings of ModernBERT-base: - anchor is a learned token, initialised from the " image" embedding. - alpha is a scalar gate, initialised to 0, so the model starts as exactly the text-only model. - gmax caps…
VNPen is MewBaka Studio's visual-novel model series. The writer edition is for script writing, de-AI rewriting, and generating example scenes from a mood brief. Output format is one script line per line: speaker：text, with narration written as 旁白：. The base Qwen/Qwen3.5-2B is multimodal. Its checkpoint carries 297 model.visual. tensors (a depth-24 / hidden-1024 / patch-16 ViT) and 15 mtp. tensors for multi-token prediction. This project is text-only. In transformers, AutoModelForCausalLM on a qwen35 config builds Qwen35ForCausalLM over a Qwen35TextConfig — so the vision weights were never loaded at any point: not for training, not for merging, not for saving. Verified on the published…
The voice of an AI, written down and checkable. voaice is the voice stack of mindX: speech in, speech out, measured throughout. It gives a machine a voice, says the realm's names the way their owners say them, and proves which voice made a recording. This repository is voaice's voice library: 70 open-licensed Piper voices in 29 language families (4.62 GB), kept here so a mindX node holds only the voices it speaks with and fetches any other on demand. The voices in piper/ are here for anyone to use: download one, run it with Piper, build on it. Each voice keeps its own open licence, the licence of the dataset its speakers recorded, and the folder's official licences list every voice under…
The Von System One decision model (ModernBERT-large, 395M, English, 8192-token context), exported to ONNX fp32 and packaged for Verdict -- a high-performance serving engine for System One decision models. Serve it with one command: Pick the image that matches the host. The -v mounts cache the model, so only the first run downloads it. Add -e VERDICTUSEMODELSCOPE=1 and use sgyaqing/von to fetch from ModelScope instead of the hub; add -e HFENDPOINT=https://hf-mirror.com if the hub is slow or unreachable. Endpoints: the standard decision protocols POST /v1/systemone and POST /v1/decisions, native POST /v1/choice | /v1/score | /v1/noul, plus an OpenAI-compatible layer (/v1/chat/completions…
This repository hosts app-managed OCR runtime archives for Vox Jot. The runtime archive contains the ocrruntime Python sidecar package and its Python dependencies for neural Screen OCR backends. The archive does not contain Vox Jot credentials, signing material, user data, transcripts, or private app distribution secrets. It also does not contain OCR model weights; Vox Jot downloads model weights through the app's OCR model catalog. - ocr-runtime-macos-aarch64-all.tar.gz: macOS Apple Silicon runtime bundle. - ocr-runtime-macos-aarch64-all.tar.gz.sha256: SHA-256 checksum consumed by the app before extraction. - ocr-runtime-linux-x64-all.tar.gz: Linux x64 runtime bundle.…
A lightweight standalone audio feature extractor derived from Voxtral-Mini-3B-2507. This repository isolates the Whisper-based audio encoder and multi-modal projector from the original 3B language model. The extracted module is intended for offline audio preprocessing, dataset preparation, feature caching, and downstream multimodal training pipelines. The language-model decoder is not included. It does not contain the 3B LLaMA language-model decoder. For offline preprocessing, loading the complete multimodal language model is unnecessary when the only required output is the projected audio representation. This standalone checkpoint can therefore be used as a dedicated audio feature…
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.