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 2026-10-21 · How the library is built
12,010 models, sorted by most downloaded.
licensename: swift-open-license-1.0 licenselink: https://huggingface.co/ukisai/Swift-Qwen3.8-27b/blob/main/LICENSE libraryname: transformers pipelinetag: image-text-to-text - qwen38 - efficient-thinking - reasoning - token-efficient - genesis - lora basemodel: ukisai/Swift-Qwen3.8-27b basemodelrelation: finetune
LoRA adapters from the bad-rl project: stories about an AI that declines to reward hack (flagging broken tests instead), trained into language models before RL. Each folder is a PEFT adapter; load it onto the model named below with PeftModel.frompretrained. 1M / 3M / 10M = story tokens seen. Grafting is only valid when the chat model was post-trained from the base it is applied over (check with rl/lineagecheck.py: Qwen3-4B 0.996, Qwen3.5-9B 1.0, Gemma 3 12B 0.979, Gemma 3 27B 0.983, Qwen3-14B 0.997, Nemotron 12B v2 0.997, Llama 3.1 8B 0.999 weight cosine). Grafting (Nutter, Roytburg, Dumas, Ou, Feng 2026, arXiv 2610.00767): train on the pre-trained checkpoint, add the learned update to the…
PPO policies for a two-wheeled balancing robot (wheeled inverted pendulum), trained in MuJoCo Warp via mjlab with rslrl and cross-checked against a PyBullet oracle. Each policy is an ONNX file laid out as /model.onnx. The run name is the training recipe; results for each are in the source repo's TRAININGLOG.md. Older entries are raw rslrl.pt checkpoints (below). Several observation interfaces live in this repo. The sk runs are the runs are interface-ablation artifacts, and they differ from each other as well as from sk: ablcombo is 10 inputs wide, while ablnolpfjerk1 keeps all 40 and changes what one channel means. Read the width and the filter constants from each file's metadata rather…
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Bangla speech recognition: a 65.5M-parameter Zipformer transducer, fine-tuned from an English LibriSpeech model on about 1,210 hours of Bangla speech. CPU-friendly ONNX versions (fp32 / fp16 / int8): SayedShaun/bangla-zipformer-onnx. The model code comes from icefall, so you need to install it and a few packages once: Accepts a file path (wav / flac / ogg...) or (samples, samplerate). Don't want to install icefall and k2? Use the ONNX version, which needs only onnxruntime. asr.py is a thin wrapper. To use the weights directly, set up icefall as in the quick start (ICEFALLROOT), then: Full dev (5,282 utterances, 8.1 h) and test (10,485 utterances, 16.4 h) sets. WER counts punctuation…
This repository supplies trained model artifacts for the reviewed historical handwriting recognition solution. The code package is delivered separately to the organizers. It contains no competition images, label tables, OCR predictions or submission CSVs. Reported public score: 0.927525446. WER Weighted: 1.306287832. CER Weighted: 1.985048359. Private score: not supplied. manifest.json maps every checkpoint and fitted selector to a SHA256-addressed file under weights/. Identical files share one stored object. Restore each targetpath beneath the configured trained-model directory and link it into the runtime workspace. The organizer code package pins a completed commit. Public pretrained…
When a caller starts talking while a voice agent is still speaking, should the agent stop? This model makes that decision from text, in a few milliseconds. It reads one moment of a call: what the agent had already said, what it was about to say, and the caller's speech-recognised words. It then returns the probability that the agent should stop (INTERRUPT) or keep talking (CONTINUE). The CPU-friendly model: 38 ms per decision on 4 CPU threads. It matches the 400m on held-out business types and real calls, and gives up about 2 points under distribution shift. Have a GPU? bargein-classifier-ettin-400m is the flagship: more robust to distribution shift, at 8.5 ms on a GPU. Callers talk over…
When a caller starts talking while a voice agent is still speaking, should the agent stop? This model makes that decision from text, in a few milliseconds. It reads one moment of a call: what the agent had already said, what it was about to say, and the caller's speech-recognised words. It then returns the probability that the agent should stop (INTERRUPT) or keep talking (CONTINUE). The flagship model: the most robust to distribution shift (2 points ahead of the 150m on OOD-10k), at ~9 ms per decision on a GPU. Need CPU-only inference? bargein-classifier-ettin-150m runs in 38 ms on 4 CPU threads. Callers talk over voice agents all the time, and most of it should not stop the agent: "mm…
not-for-all-audiences
not-for-all-audiences
not-for-all-audiences
not-for-all-audiences
Explains a Bash command line in exactly one English sentence, phrased as an instruction starting with a verb. QLoRA fine-tune of Qwen/Qwen2.5-Coder-3B-Instruct, merged and quantized to q4KM. The Modelfile pins the system prompt and this decoding: 920 held-out commands Judge columns are claude-sonnet-5 scoring a fixed 200-command subset. Apache-2.0, matching the base model, whose weights this GGUF contains. Training data comes from the nl2bash project; consult it for the terms attached to that corpus.
Explains a Bash command line in exactly one English sentence, phrased as an instruction starting with a verb. QLoRA fine-tune of Qwen/Qwen2.5-Coder-7B-Instruct, merged and quantized to q4KM. The Modelfile pins the system prompt and this decoding: 920 held-out commands Judge columns are claude-sonnet-5 scoring a fixed 200-command subset. Apache-2.0, matching the base model, whose weights this GGUF contains. Training data comes from the nl2bash project; consult it for the terms attached to that corpus.
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.