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 2026-10-19 · How the library is built
11,442 models, sorted by most downloaded.
基于明前奶绿歌声数据集 v2（1,057 段 / 50.3 分钟，全量去混响）训练的 RVC v2 声音转换模型：48 kHz、HiFi-GAN 声码器、Titan 底模微调 200 轮（26,800 步）、RMVPE 音高提取。 - mingqiannailvv2final.pth：推理用模型权重（RVC 格式，内含生成器与配置） - mingqiannailvv2.index：音色检索索引 1. 两个文件放入 logs/mingqiannailv/ 目录（没有就新建） 3. 参数建议：音高调整 0、索引率 0.3~0.5、protect 0.33
static quants of https://huggingface.co/omneity-labs/miniagent-1.7B-strapi 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…
This repository contains the latest 30,000-step post-training checkpoint from the StarVLA MiniCPM-GR00T experiment on the BananaInBowl HDF5 dataset. The main weight file is steps30000pytorchmodel.pt. The model was initialized from the 145,000-step DROID pretraining checkpoint and trained with two RGB views resized directly to 448x448, a 15-step action horizon, and 8-dimensional state/action vectors. This is a StarVLA training checkpoint rather than a standalone Transformers frompretrained model. Use the matching StarVLA code and the included config.full.yaml to load it.
Dedicated deployment cache of upstream public assets. Contains four hash-pinned base assets from Comfy-Org/MiniMax-H3 plus three pinned DMAD/LightX2V adapters. All weights use the provider native cache; no weights are baked into the worker image. Upstream licenses and use restrictions apply. The standard MiniMax-H3 license excludes the US, EU, UK and South Korea; this mirror does not grant additional rights to recipients. Read LICENSE and NOTICE before use. The text encoder incorporates Apache-2.0-licensed Qwen3-VL-32B: https://github.com/QwenLM/Qwen3-VL/blob/main/LICENSE. Do not update main after qualification; create a new cache repository for changes.
All the essential MiniMax H3 LoRas in one place!
minimind-math-v3 是一个基于 MiniMind 项目从零训练的小型中文数学语言模型，权重已转换为 Qwen3 兼容格式，可直接使用 HuggingFace transformers 加载推理。 - 架构：Dense Transformer（Decoder-only），未使用 MoE - 数据：以数学/推理语料为主的预训练数据（pretraint2tmini.jsonl），并经过数学 SFT 训练 - Tokenizer：基于 MiniMind 自训 tokenizer 修改的 patched tokenizer，详见下方说明 本模型的预训练与 SFT 均基于 jiwubu/minimind 代码仓库完成。相对上游 jingyaogong/minimind 的主要修改是新增 math/ 目录，用于生成数学 SFT 用的加减乘除算术数据（genmathdataaddsub.py、genmathdatamuldiv.py 等），并提供配套评测脚本（evalmath.py）。 最简单的方式是用仓库自带的交互式验证脚本（chat template + 贪心解码 + 流式输出）： 或直接用 transformers： - 预训练 2 个 epoch，batch size 32，最大序列长度 340 - 优化器 AdamW，初始学习率 5e-4（带 warmup + 余弦衰减） - 混合精度：bfloat16 本模型使用基于 MiniMind 原版 tokenizer 修改的 patched tokenizer（Sequence[Digits, ByteLevel]）：…
Full-parameter fine-tuning for TLINK temporal relation classification. mistralai/Ministral-8B-Instruct-2410 AnirbanSaha/tlink-classification-sentence-only The evaluation/ directory contains predictions, the classification report, confusion matrix, and a machine-readable evaluation summary.
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.