This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Evaluated with EmbeddingSimilarityEvaluator Approximate statistics based on the first 100 samples: "scale": 20.0, "similarityfct": "cossim", "gatheracrossdevices": false, "directions": [ "querytodoc" "partitionmode": "joint", "hardnessmode": null, "hardnessstrength": 0.0 bibtex title = "Sentence-BERT: Sentence Embeddings using…
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.
12,010Models
3,413Datasets
288Papers
7,298Publishers
12,421Sourced relationships
Updated 2026-10-21 · How the library is built
12,010 models, sorted by most downloaded.
[[Paper]](https://arxiv.org/abs/2206.04658) - [[Code]](https://github.com/NVIDIA/BigVGAN) - [[Showcase]](https://bigvgan-demo.github.io/) - [[Project Page]](https://research.nvidia.com/labs/adlr/projects/bigvgan/) - [[Weights]](https://huggingface.co/collections/nvidia/bigvgan-66959df3d97fd7d98d97dc9a) - [[Demo]](https://huggingface.co/spaces/nvidia/BigVGAN) - General refactor and code improvements for improved readability. - Fully fused CUDA kernel of anti-alised activation (upsampling + activation + downsampling) with inference speed benchmark. - We provide pretrained checkpoints of BigVGAN-v2 using diverse audio configurations, supporting up to 44 kHz sampling rate and 512x upsampling…
[[Paper]](https://arxiv.org/abs/2206.04658) - [[Code]](https://github.com/NVIDIA/BigVGAN) - [[Showcase]](https://bigvgan-demo.github.io/) - [[Project Page]](https://research.nvidia.com/labs/adlr/projects/bigvgan/) - [[Weights]](https://huggingface.co/collections/nvidia/bigvgan-66959df3d97fd7d98d97dc9a) - [[Demo]](https://huggingface.co/spaces/nvidia/BigVGAN) - General refactor and code improvements for improved readability. - Fully fused CUDA kernel of anti-alised activation (upsampling + activation + downsampling) with inference speed benchmark. - We provide pretrained checkpoints of BigVGAN-v2 using diverse audio configurations, supporting up to 44 kHz sampling rate and 512x upsampling…
A Bidirectional LSTM that classifies Indonesian public comments about a government policy (the Kopdes program) into three sentiment classes: Negatif, Netral, and Positif. The model is trained from scratch (no pretrained embeddings) on a small dataset, so treat it as a course/research-level baseline rather than a production classifier. - About 850 unique comments remained after preprocessing and deduplication. - Labels are not human-annotated. They were generated automatically with the InSet lexicon: score = (number of positive words) − (number of negative words) in the stemmed text. Score > 0 is Positif, < 0 is Negatif, and 0 is Netral. Because of this, the reported scores measure how well…
Model Card: BioMistral-Cardiac-ACSMOverviewDeveloper: Bilal JaouadBase Model: BioMistral/BioMistral-7B-BnB.4Domain: Cardiovascular rehabilitation and ACSM clinical exercise prescription.Methodology: Domain adaptation (continued pre-training) via QLoRA (4-bit NF4 quantization, LoRA rank $r=16$) on an NVIDIA T4 GPU.Training DatasetThe model was adapted on a rigorously cleaned and curated corpus comprising five core reference documents:Patient Workbook: A 120-page cardiac rehabilitation patient education manual (with blank progress logs filtered out).Clinical Guidelines: The 146-page CPG STEMI 2019 guidelines, utilizing Camelot for structured table extraction.Clinical Protocols: The Malaysian…
что нужно, чтобы за несколько минут начать управлять живым Blender кодом. Никаких предварительных знаний о Blender, Python или MCP не требуется — только этот документ. Кому адресовано: агенту (Claude, GPT, Gemini, локальной модели — любой), которого подключили к Blender и который не знает, с чего начать. Читай по порядку. Статус: проверено на живом Blender 5.2.1 LTS, аддон blend-ai v1.3.0, Windows 11. 1. Blender: N в 3D-вьюпорте → вкладка blend-ai → Start Server (порт 9876). 2. Скачать: git clone https://github.com/HoldMyBeer-gg/blend-ai + uv pip install -e. 3. Проверить связь: отправить {"command": "getsceneinfo"} на 127.0.0.1:9876. Ключевое, что нужно понять: Blender — это сервер. Он…
This repository is a compact, custom PyTorch implementation of Blip for Generation. 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…
This repository is a compact, custom PyTorch implementation of Blip for Classification. The base 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 polynomial schedule. These are…
Working implementation of Blip for Matching 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 adafactor with a onecycle schedule. These are starting values in the script, not evidence of a…
Working implementation of Blip for Matching 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 adamw with a onecycle schedule. These are starting values in the script, not evidence of a…
This is an experimental Blip codebase for Retrieval. It keeps the xlarge 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 lion with a constant warmup schedule. These are starting values in the script, not evidence of a completed run.…
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.