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.
Updated 2026-10-20 · How the library is built
11,734 models, sorted by most downloaded.
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 64 - evalbatchsize: 64 - lrschedulertype: linear - numepochs: 2 - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 32 - evalbatchsize: 32 - lrschedulertype: linear - numepochs: 10 - Transformers 5.18.0 - Pytorch 2.11.0+cpu - Datasets 5.0.1 - Tokenizers 0.23.2
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).
LoRA adapters from a research sprint asking whether safety transfers subliminally through distillation. Report and code: https://github.com/Realmbird/distilling-safety (see reports/REPORT.md). Research artifacts, not for deployment. Several students are measurably less safe than the base model (that is the main finding); none of these adapters should be used as a safety intervention. All adapters sit on Qwen/Qwen2.5-7B-Instruct ("M0"). Teacher recipe: LoRA r=64, alpha=64, all attention and MLP projections; lr 1e-4, cosine schedule, 1 epoch, batch 16, max length 1024; completion-only loss. Data: LLM-LAT/harmful-dataset (2.5k-prompt training split) and LLM-LAT/benign-dataset (2.5k rows)…
This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 3.0 - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
A small Mobilevit implementation for Classification, packaged with an explicit configuration and an initialization checkpoint. The nano 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 linear warmup schedule. These are starting values in the script…
Download engine API (yt-dlp + ffmpeg) for VidMax and GramMax.
This repository is a compact, custom PyTorch implementation of Beit for Generation. The huge 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 novograd with a constant warmup schedule. These…
Working implementation of CLIP for Retrieval using a small configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - 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 adafactor with a exponential schedule. These are starting values in the script, not evidence of a…
CPU-only page classifier for text extracted from PDFs (no OCR), designed for, "label": one of invoice|lab|radiology|dischargesummary}, split train/val/test. Point steps 2-4 at it with --data-dir; re-calibrate thresholds on your val split before deploying. Note traintransformer.py targets transformers==4.57. — 5.x removed several TrainingArguments kwargs this script uses. - Live-metrics trackio dashboard could not be hosted on this account (Gradio Spaces require PRO), so run metrics live in the job logs.
This is an exploratory note for Document AI. It records the intended comparison, likely confounders, and reproducibility requirements before any benchmark result is reported. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as FUNSD, SROIE, and CORD - reproducibility checks, failure modes, and open questions - topic-relevant references Start with papernotes.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs. The note is intentionally…
This is an exploratory note for Document AI. It records the intended comparison, likely confounders, and reproducibility requirements before any benchmark result is reported. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as FUNSD, SROIE, and CORD - reproducibility checks, failure modes, and open questions - topic-relevant references Start with papernotes.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs. The note is intentionally…
This is an ONNX version of Jwalit/document-moire-detector. It was automatically converted and uploaded using this Hugging Face Space. See the pipeline documentation for image-classification: https://huggingface.co/docs/transformers.js/api/pipelines#modulepipelines.ImageClassificationPipeline A fine-tuned DeiT-small Vision Transformer for detecting moiré patterns in document images. (common from screen photography, scanning, or screen captures). - clean (0): No moiré patterns - moire (1): Moiré patterns detected 1. Resize aliasing — downscale+upscale with NEAREST interpolation + pattern overlay 2. Pattern overlay — sinusoidal interference with per-channel color variation 3. Multi-frequency…
A forensic segmentation network that finds where a payslip was edited — copy-move, splice from another document, or a re-typed amount — and the small models and thresholds that turn its pixel map into a verdict an analyst can act on. Part of docverify, a complete system with arithmetic checks, PDF forensics and a local LLM note: TamperNet (~33M parameters): a pretrained ConvNeXt encoder on RGB, plus two forensic inputs — fixed SRM noise residual filters (edits break the sensor/print noise) and a JPEG/DCT branch (a pasted region carries its own 8×8 compression grid) — fused into a U-Net-style decoder that outputs one logit per pixel. The page score is the mean of the top-200 pixel logits.…
Finds the 10 fields of a French payslip so that an edit found by the tamper model can be pinned to net pay or gross salary instead of "pixels at (812, 640)". In docverify, an edit inside a money field is what turns a page into high risk. Part of docverify: project · netpaye (net pay) · brut (gross salary) · salairebase (base salary) · netavantimpot (net before tax) · cotisations (total contributions) · test pages, scans and phone photos mixed. 19 ms per page on a T4; part of the 6.7 s full pipeline on 4 CPU threads. Synthetic French payslips only (generated, fake people and companies); other layouts need their own field list. AGPL-3.0, inherited from Ultralytics YOLO. The rest of docverify…
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.