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.
11,442Models
3,247Datasets
285Papers
6,976Publishers
12,091Sourced relationships
Updated 2026-10-19 · How the library is built
11,442 models, sorted by most downloaded.
Final checkpoints of the PDE-OBS campaign: one model per (PDE family, method, training observation pattern). Each checkpoint is the final recorded checkpoint of its attempt, not one selected on validation or test error. This repository accompanies an anonymous submission under double-blind review. The cluster labels (cluster-A, cluster-B, cluster-C) stand for the three machines the campaign ran on; they carry no institutional meaning. The architecture is rebuilt from the benchmark's own registry, for example: - Weights only by default. Optimizer, gradient-scaler and RNG states were removed (about two thirds of each file); droppedkeys in the manifest records this per checkpoint. The…
Working implementation of Perceiver for Generation using a large 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 adam with a cosine schedule. These are starting values in the script, not evidence of a…
This repository is a compact, custom PyTorch implementation of Perceiver for Classification. 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 rmsprop with a polynomial schedule.…
This repository is a compact, custom PyTorch implementation of Perceiver for Generation. The giant 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 lion with a step schedule. These are…
A research-oriented Perceiver prototype targeting Generation. The included giant setup documents defaults and file formats without presenting unverified performance numbers. - 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 adam with a polynomial schedule. These are starting values in the script, not evidence of a completed run. For…
A small Perceiver implementation for Matching, 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 rmsprop with a step schedule. These are starting values in the script, not evidence…
This repository is a compact, custom PyTorch implementation of Perceiver for Retrieval. The xlarge 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 adamw with a cosine schedule. These are…
This is an experimental Mobilevit codebase for Generation. It keeps the base 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 rmsprop with a cosine schedule. These are starting values in the script, not evidence of a completed run.…
Every model published in lab-cosmo/upet (the PET-MAD / UPET family), converted for pet-kokkos, a C++/Kokkos implementation of PET that runs without libtorch on CPUs and on NVIDIA and AMD GPUs. The weights are unchanged from upstream. Each model is two files:.json holds the hyperparameters, species map and composition energies, and.safetensors holds the weights. They were produced with tools/convertpet.py, and each JSON's sourcemodel names the checkpoint it came from. pet-kokkos looks for models by name in $PETMODELDIR,./models,., and ~/.local/share/pet/models. For what each model was trained on and the level of theory behind it, see the upstream model card. Please cite the upstream work…
Peta1 is an autonomous software engineering agent checkpoint based on google/gemma-4-E4B-it (4.3B active parameters), post-trained using a targeted three-stage curriculum: 1. Tree-of-Reasoning (ToR) SFT: Supervised deliberation in Gemma 4's native latent thinking tokens ( thought) enforcing hypothesis formulation, environment simulation, and branch pruning. 2. Capability Frontier Discovery: Screening of candidate tasks (G = 4, T = 0.7) to isolate the 18% informative frontier band (0 < p < 1.0), preventing policy gradient collapse from trivial (36%) and impossible (46%) tasks. 3. Verifiable Outcome GRPO: Policy gradient optimization with verifiable rewards (Rtarget + Rformat + Rtor - lambda…
petal-w1 turns raw dictation into the text you meant to type. It is the on-device cleanup model in Petal, a free macOS dictation app. It runs with MLX on Apple silicon. It is a full fine-tune of Qwen3.5-0.8B, and it does one job: - Removes fillers, stutters, false starts, and verbal tics ("you know what I mean?"). - Keeps only the final version of a self-correction ("Friday, no wait, Thursday" becomes "Thursday"), also when speech recognition mishears the correction words. - States a point once when the speaker repeats it in different words, and keeps every detail. - Condenses rambles into clear sentences, and keeps every fact, name, number, and request. - Keeps questions as questions and…
petal-w1 turns raw dictation into the text you meant to type. It is the on-device cleanup model in Petal, a free macOS dictation app. It runs with MLX on Apple silicon. It is a full fine-tune of Qwen3.5-0.8B, and it does one job: - Removes fillers, stutters, false starts, and verbal tics ("you know what I mean?"). - Keeps only the final version of a self-correction ("Friday, no wait, Thursday" becomes "Thursday"), also when speech recognition mishears the correction words. - States a point once when the speaker repeats it in different words, and keeps every detail. - Condenses rambles into clear sentences, and keeps every fact, name, number, and request. - Keeps questions as questions and…
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.