Private checkpoint repository. Current M3 exploration uses M3 Simple step 7365. M3 step 7365 includes model and optimizer. Pixel VAE and the repaired fixedskins20260917 dataset are required separately. Old M3 step 26000 and the old step 3300 identity encoder have been removed from the current branch at the owner's request; historical revisions remain available. Other model repositories, datasets and training bundles were not changed. Complete M2 model and dependency guide: Pixel VAE, optional video backbone, separate vocabularies, latent normalization, and M4 text cache. M2 and M3 item ID 12 differ; see the guide before coupling them.
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.
static quants of https://huggingface.co/ysharma/pocket-layout-planner-2B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
Clone of Pocket TTS 6l model only. Use of our model must comply with all applicable laws and regulations and must not result in, involve, or facilitate any illegal, harmful, deceptive, fraudulent, or unauthorized activity. Prohibited uses include, without limitation, voice impersonation or cloning without explicit and lawful consent; misinformation, disinformation, or deception (including fake news, fraudulent calls, or presenting generated content as genuine recordings of real people or events); and the generation of unlawful, harmful, libelous, abusive, harassing, discriminatory, hateful, or privacy-invasive content. We disclaim all liability for any non-compliant use. - Kyutai for the…
Specialized conversion of Kyutai Pocket TTS. This profile supports English text with the predefined alba voice and returns mono 24 kHz Float PCM, including incremental audio. Glade is a native Swift library for speech inference on Apple silicon, using Core AI, Core ML, and model-specific host implementations. Its runtime source is currently private. This repository distributes the model assets and runtime metadata used by that library. Python is export/measurement tooling, not an application dependency. Mac qualification is included; iPhone and Watch qualification is not claimed. Download weights and configuration from one snapshot. The approximately 117.2 MB bundle uses W8A16 language…
Optimized ONNX exports of Pocket TTS for high-speed, memory-efficient text-to-speech and zero-shot voice cloning on CPU, mobile, and edge runtimes. Mirrored and validated from KevinAHM/pocket-tts-onnx at commit 58a6d00cf13d239b6748cb0769f35c580a8f606c. This repository provides comprehensive support for both compact 6-layer models and high-capacity 24-layer models: - 6-Layer Compact Models: english2026-04, german, italian, portuguese, spanish - Ideal for lightweight CPU inference, mobile devices, and low-latency streaming. - ~302 MB FP32 / ~76 MB INT8 Flow LM. - 24-Layer Capacity Models: french24l, german24l, italian24l, portuguese24l, spanish24l - High-fidelity modeling for complex prosody…
Bro, imagine an AI that can see, hear, and read a website while hunting bugs at the same time. Yeah, that's PolyglotBugHunter-X. Try it live — one click, no install, no server, runs in your browser. A multimodal agent for automated web security testing. It reads pages (text), looks at rendered output (image), and listens to uploads (audio) at the same time, then reports what it found with CVSS v3.1 scores and evidence you can re-check. It ships 43 detection payloads across 8 bug classes (24 of them polyglot — single strings that are simultaneously plausible HTML, JS, SQL and shell), a payload-routing engine that guesses the right vector from the parameter name, and a scoring profile. This…
Does the "best" polyp detector stay the best if you train it differently? This repository releases every model from a controlled benchmark that answers that question: 12 detectors × 3 white-light colonoscopy datasets × 6 training regimes × 3 seeds = 648 best.pt checkpoints, together with cached per-image predictions and ensemble outputs. RT-DETR-X (seed 88) on two Kvasir-SEG test frames under the Scratch, Pretrained and Aug-10× regimes. Green = reference box, cyan = matched detection, pink = unmatched detection (score > 0.20, IoU ≥ 0.50). These examples are illustrative, not typical accuracy. Only the 648 completed canonical runs are included. Interrupted runs, last.pt files, worker logs…
A research-oriented Poolformer prototype targeting Contrastive. 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 onecycle schedule. These are starting values in the script, not evidence of a completed run. For…
A research-oriented Poolformer prototype targeting Classification. The included nano 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 adamw with a linear warmup schedule. These are starting values in the script, not evidence of a completed…
Working implementation of Poolformer for Classification 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 adam with a constant warmup schedule. These are starting values in the script, not…
This repository is a compact, custom PyTorch implementation of Poolformer for Retrieval. The nano 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 adam with a exponential schedule. These are…
This repository is a compact, custom PyTorch implementation of Poolformer for Matching. The nano 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 exponential schedule. These are…
A small Mobilevit implementation for Matching, packaged with an explicit configuration and an initialization checkpoint. The small 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 cosine schedule. These are starting values in the script, not…
This is an exploratory note for OCR Freeform. 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 notes.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…
Direct preference optimisation on top of the corrective SFT, 2 epochs over 8,383 preference pairs. Intended to move the model from 'roughly right structure' to 'exactly right structure'. Fine-tuned from CheneyWong/povl-sft-2d-merge, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. The gain is within sampling…
On-policy distillation. The weight delta learned by the teacher was merged into the SFT base with an extra scale of 0.5, the best point of an alpha sweep (0.25 -> +0.32, 0.5 -> +0.44, 0.75 -> -0.29, 1.5 -> -3.01 with t = -12.42). Fine-tuned from CheneyWong/povl-sft-2d-merge, which is NOT the RL checkpoint -- the teacher delta was merged into the SFT base, which is why it neither clearly beats nor clearly follows round 2. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly…
The teacher used for on-policy distillation: final checkpoint of a dedicated teacher SFT run (2,367 steps). Fine-tuned from PaddleOCR-VL-1.6 (base), which is trained separately from the student chain on a teacher-specific data mixture. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (never gated on the public sets -- see Known limitations) (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. Teacher qualification was…
Reinforcement learning round 1, DAPO algorithm, 400 steps. Fine-tuned from CheneyWong/povl-dpo-2ep, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. Only works with DAPO's dynamic sampling. The first attempt with GSAPO had 78% of groups contributing zero gradient (49.0% saturated, 16.5% identical rewards, 12.6%…
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.