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.
ONNX conversion of cua-ai/cua-s1-forms, prepared for lightweight local inference experiments with ONNX Runtime, ONNX Runtime Web, WebAssembly (WASM), and WebGPU. Please read the original model card before using this conversion. It contains the authoritative description of the model's architecture, training setup, evaluation, limitations, and intended scope. CUA-S1 Forms is a small specialist "System One" model for form-oriented computer-use tasks. Unlike an autoregressive LLM, it does not generate text token-by-token. For each UI element, it receives: 1. a short structured context describing the task, form, and element, and 2. a set of candidate options such as extracted document values…
act policy trained via Vibe Data Studio on 20 teleop episodes. Language-conditioned — pass one of these instructions at inference: - Action/state (7-dim): shoulderpan, shoulderlift, elbowflex, wristflex, wristroll, gripper, tilt - Cameras @ 20 fps: base 640×480, top 640×480, wrist 640×480 - Consumed image inputs (the checkpoint's resolved VISUAL features, from its config.json): observation.images.base, observation.images.top, observation.images.wrist Materialized collection cucumbergraspacttrainvibepi20260922@v1 (frozen 2026-09-23): - autoresearch-vibepi-000655-task-cucumbergrasp @ d55dfe57 (1 eps) - autoresearch-vibepi-000656-task-cucumbergrasp @ ffba74e6 (1 eps)…
用《密教模拟器》(Cultist Simulator) 的游戏内文本微调 Qwen/Qwen3-4B 得到的文本生成模型。 仓库根目录带 LLaMA-Factory 生成的 Modelfile，下载后在本目录下执行： - 4B：The light leaks through cracks. My mind is clearer than it's been in any other time. 标记完整保留 - 0.6B：Light leaks through a Crack in the Skin. My brain is clearer than ever at any given time. 标记全丢 - 训练语料全部抽取自《密教模拟器》游戏本体，版权归 Weather Factory 所有。 - 基座模型 Qwen/Qwen3-4B 采用 Apache-2.0 协议，本仓库的权重是它的微调衍生品。
This model classifies a machine-specific ROI into: - EMPTY - CUP - UNDEFINED - EMPTY -> [0, 0] - CUP -> [1, 0] - UNDEFINED -> [0, 1] Output 0 represents CUP vs EMPTY. Output 1 represents UNDEFINED. The ROI selection is handled outside the model. The model receives the cropped machine ROI.
This is an exploratory note for Cross Modal Fusion. 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 task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with review.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…
Working implementation of ViT for Generation using a huge 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 lion with a linear warmup schedule. These are starting values in the script, not evidence of a…
If you take one thing from this page: this model does not do customer service. It watches something else do customer service and vetoes bad steps. Everything below walks you through that idea, then the evidence, then the exact commands. Imagine a support agent (human or AI) working a ticket. The work is a loop: look up the caller, check their history, open a case, log the call. The dangerous mistake is doing steps out of order — logging a call when no case exists means the record vanishes. This model sits beside that loop and answers four questions about the current situation: 1. nexttool — "which step comes next?" (look up / check history / open case / log call) 2. safetolog — "does a case…
2,400 LLM-inferred (state, question, answer) rows in strands-decider Example format (kind/state/instructions/options/label/task/weight/instructionvariants), split evenly: 120 rows × 20 decision types, all states unique, all labels in range, all rows schema-validated. Generation: four parallel subagents, each inventing realistic 2026 CX states (subscriptions, SSO, renewals, invoices, chat, fraud, SLA, PII) and judging the correct label by model inference. No scripts, no templates, no rule-based synthesis. Score labels spread evenly across levels (unlike v1's urgency rows, which were 99% one class). Continual-train checkpoint for a strands-decider model (append to trainfiles; the 20 task…
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.