# Open-Weight Models Under BSD 3-Clause License Source: https://savrn.com/models/licenses/bsd-3-clause Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by License # Open-Weight Models Under BSD 3-Clause License 108 open-weight models released under BSD 3-Clause License in the SAVRN Model Hub, with Massachusetts Institute of Technology, Ssmiththomas and Salesforce AI Research publishing the most. 108Models 102Publishers 17K to 470MParameter range 1Licenses YesCommercial use ## What BSD 3-Clause License Allows The BSD 3-Clause License is permissive. It permits commercial use and redistribution with the copyright notice, and forbids using the authors' names to endorse derived products without permission. [Read the license text](https://opensource.org/license/bsd-3-clause). ## SAVRN's Take One requirement, one prohibition, and that is the whole of it. BSD 3-Clause lets you run the weights commercially and pass them on, provided the copyright notice travels with them, and it bars you from putting the authors' names on a product built from their work unless they agree. In your own racks that means the notice stays in the model directory, the publisher stays out of your product name, and nothing in the license touches how or whom you serve or what you charge. Nine models on our hub carry it. Massachusetts Institute of Technology has three and Salesforce AI Research two; the rest come one each from Priscila, Jonas Hartmann, Alberto G. Jimenez and Shanlsl96. The work leans toward perception: three audio classifiers, two image to text models, four with no task tagged. Salesforce's blip-image-captioning-base draws the traffic, 1,710,185 downloads a month on a 512 token context, ahead of MIT's ast-finetuned-audioset-10-10-0.4593 at 687,536 and 87M parameters, and blip-image-captioning-large at 539,198 and 470M. None of it needs a card to itself. The audio classifier wants 0.2 GB at 16-bit and the large captioner 1.1 GB, so the cheapest rental the Index prices, one MI300X at $1.85 an hour, is a whole accelerator for a job that rides beside whatever else runs there. Check the endorsement clause before your marketing leans on where the model came from; it is the one line here that can bite. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [blip-image-captioning-base](https://savrn.com/models/blip-image-captioning-base) | Salesforce AI Research | — | bsd-3-clause | 1.3M | — | | [ast-finetuned-audioset-10-10-0.4593](https://savrn.com/models/ast-finetuned-audioset-10-10-0-4593) | Massachusetts Institute of Technology | 87M | bsd-3-clause | 1.3M | 1x MI300X, $1.85/hr | | [blip-image-captioning-large](https://savrn.com/models/blip-image-captioning-large) | Salesforce AI Research | 470M | bsd-3-clause | 539.2k | 1x MI300X, $1.85/hr | | [ast-finetuned-audioset-14-14-0.443](https://savrn.com/models/ast-finetuned-audioset-14-14-0-443) | Massachusetts Institute of Technology | 86M | bsd-3-clause | 8.4k | 1x MI300X, $1.85/hr | | [ast-finetuned-speech-commands-v2](https://savrn.com/models/ast-finetuned-speech-commands-v2) | Massachusetts Institute of Technology | 85M | bsd-3-clause | 7.8k | 1x MI300X, $1.85/hr | | [beewatch_ast_3class](https://savrn.com/models/beewatch-ast-3class) | Jethro Tababa | 86M | bsd-3-clause | 20 | 1x MI300X, $1.85/hr | | [multitask-scratch](https://savrn.com/models/multitask-scratch) | Priscila | 49,600 | bsd-3-clause | — | 1x MI300X, $1.85/hr | | [coca-baseline](https://savrn.com/models/coca-baseline) | Jonas Hartmann | 24,832 | bsd-3-clause | — | 1x MI300X, $1.85/hr | | [course-generation](https://savrn.com/models/course-generation) | Alberto G. Jimenez | 16,576 | bsd-3-clause | — | 1x MI300X, $1.85/hr | | [retrieval-tryout](https://savrn.com/models/retrieval-tryout) | Shanlsl96 | 33,088 | bsd-3-clause | — | 1x MI300X, $1.85/hr | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Massachusetts Institute of Technology](https://savrn.com/model-publishers/mit) | 3 | | [Ssmiththomas](https://savrn.com/model-publishers/ssmiththomas) | 2 | | [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) | 2 | | [Kevin Nugroho](https://savrn.com/model-publishers/kevinjnugroho) | 2 | | [Gabriel Nascimento](https://savrn.com/model-publishers/gnascimentoeli) | 2 | | [Zachary Gomez](https://savrn.com/model-publishers/zacharygl) | 1 | ## All 108 Models, Page 1 of 2 Model · Image to text ### [blip-image-captioning-base](https://savrn.com/models/blip-image-captioning-base) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) captioning pretrained on COCO dataset - base architecture (with ViT base backbone). Authors from the paper write in the abstract: Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the… Open weights bsd-3-clause 512 tokens transformers [View model](https://savrn.com/models/blip-image-captioning-base) Model · Audio classification ### [ast-finetuned-audioset-10-10-0.4593](https://savrn.com/models/ast-finetuned-audioset-10-10-0-4593) [Massachusetts Institute of Technology](https://savrn.com/model-publishers/mit) Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks. You can use the raw model for classifying audio into one of the AudioSet classes. See… Open weights bsd-3-clause 87M parameters transformers [View model](https://savrn.com/models/ast-finetuned-audioset-10-10-0-4593) Model · Image to text ### [blip-image-captioning-large](https://savrn.com/models/blip-image-captioning-large) [Salesforce AI Research](https://savrn.com/model-publishers/salesforce) captioning pretrained on COCO dataset - base architecture (with ViT large backbone). Authors from the paper write in the abstract: Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the… Open weights bsd-3-clause 470M parameters 512 tokens transformers [View model](https://savrn.com/models/blip-image-captioning-large) Model · Audio classification ### [ast-finetuned-audioset-14-14-0.443](https://savrn.com/models/ast-finetuned-audioset-14-14-0-443) [Massachusetts Institute of Technology](https://savrn.com/model-publishers/mit) Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks. You can use the raw model for classifying audio into one of the AudioSet classes. See… Open weights bsd-3-clause 86M parameters transformers [View model](https://savrn.com/models/ast-finetuned-audioset-14-14-0-443) Model · Audio classification ### [ast-finetuned-speech-commands-v2](https://savrn.com/models/ast-finetuned-speech-commands-v2) [Massachusetts Institute of Technology](https://savrn.com/model-publishers/mit) Audio Spectrogram Transformer (AST) model fine-tuned on Speech Commands v2. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks. You can use the raw model for classifying audio into one of the Speech… Open weights bsd-3-clause 85M parameters transformers [View model](https://savrn.com/models/ast-finetuned-speech-commands-v2) Model · Audio classification ### [beewatch_ast_3class](https://savrn.com/models/beewatch-ast-3class) [Jethro Tababa](https://savrn.com/model-publishers/troyskie) This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupsteps: 10 - numepochs: 4 - mixedprecisiontraining: Native AMP - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1 Open weights bsd-3-clause 86M parameters transformers [View model](https://savrn.com/models/beewatch-ast-3class) Model ### [aigs-hack-sep26-models](https://savrn.com/models/aigs-hack-sep26-models) [E3SM](https://savrn.com/model-publishers/e3sm-project) These are the checkpoints the latents in were recorded from. E05-FT S01 is not the shipped atmosphere (S03). The kit/ folder holds what a 2015 atmosphere run needs besides the checkpoint: the initial condition (2015-01-03 12:00), two months of forcing (the inputs only), and configs for the control and each intervention. One run uses about 4 GB of GPU memory. Every config sets seed: 0. Keep it: the model is stochastic, and a shared seed is what makes two runs comparable node for node. Change the intervention by editing the overwrite block; make it longer with nforwardsteps (the forcing covers January and February 2015). To record the latents as well, and to steer a layer along a feature, use… Open weights bsd-3-clause [View model](https://savrn.com/models/aigs-hack-sep26-models) Model ### [albef-multitask-2024](https://savrn.com/models/albef-multitask-2024) [Ssmiththomas](https://savrn.com/model-publishers/ssmiththomas) Working implementation of Albef for Multitask 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 adam with a step schedule. These are starting values in the script, not evidence of a completed… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/albef-multitask-2024) Model · Robotics ### [asimov-flex](https://savrn.com/models/asimov-flex) [Emre Can Kartal](https://savrn.com/model-publishers/eckartal) Velocity-commanded walking policy for Asimov 1, trained in Isaac Lab with PPO. It is a base walk meant for later skills to build on: forward, backward and sideways walking, turning while walking or on the spot, and standing still. The gait was shaped with a reference cycle from an everyday human walk (CMU motion capture, retargeted with GMR) and a light AMP style reward. It was then trained further for balance (pushes from every direction, steady forces, harder terrain) and for robustness to differences between simulation and the robot (IMU tilt bias, motor strength and gain changes, extra mass, command latency, joint friction, low-friction floors). A terrain height map was used by the… Open weights bsd-3-clause asimov [View model](https://savrn.com/models/asimov-flex) Model ### [assignment-contrastive](https://savrn.com/models/assignment-contrastive) [James Davies](https://savrn.com/model-publishers/jamesdavi) A research-oriented Blip prototype targeting Contrastive. The included base 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 adafactor with a cosine schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/assignment-contrastive) Model ### [assignment-retrieval-2024](https://savrn.com/models/assignment-retrieval-2024) [Viktoria Smirnov](https://savrn.com/model-publishers/vismirnov04) This repository is a compact, custom PyTorch implementation of Poolformer for Retrieval. The large 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 rmsprop with a constant warmup schedule.… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/assignment-retrieval-2024) Model ### [beit-checkpoint](https://savrn.com/models/beit-checkpoint-2) [William Martinez](https://savrn.com/model-publishers/williammar) This repository is a compact, custom PyTorch implementation of Beit for Generation. The large 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 adafactor with a cosine schedule. These are… Open weights bsd-3-clause 16,576 parameters 512 tokens [View model](https://savrn.com/models/beit-checkpoint-2) Model ### [beit-checkpoint-2024](https://savrn.com/models/beit-checkpoint-2024) [Robert Ward](https://savrn.com/model-publishers/robertward) This is an experimental Beit codebase for Generation. 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 lamb with a step schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 24,832 parameters 128 tokens [View model](https://savrn.com/models/beit-checkpoint-2024) Model ### [beit-matching](https://savrn.com/models/beit-matching) [Tyler Johnson](https://savrn.com/model-publishers/buffalogenomics) A research-oriented Beit prototype targeting Matching. The included tiny 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 sgd with a onecycle schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 49,600 parameters 128 tokens [View model](https://savrn.com/models/beit-matching) Model ### [beit-matching](https://savrn.com/models/beit-matching-2) [Do-yun Lee](https://savrn.com/model-publishers/jasminehjh) Working implementation of Beit for Matching using a nano 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 step schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 33,088 parameters 128 tokens [View model](https://savrn.com/models/beit-matching-2) Model ### [beit-retrieval-exp](https://savrn.com/models/beit-retrieval-exp) [Adrian Kowalski](https://savrn.com/model-publishers/ackowalski) A research-oriented Beit prototype targeting Retrieval. The included small 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 adafactor with a polynomial schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 24,832 parameters 512 tokens [View model](https://savrn.com/models/beit-retrieval-exp) Model ### [blip-checkpoint-2024](https://savrn.com/models/blip-checkpoint-2024) [Zachary Gomez](https://savrn.com/model-publishers/zacharygl) 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… Open weights bsd-3-clause 24,832 parameters 128 tokens [View model](https://savrn.com/models/blip-checkpoint-2024) Model · Text generation ### [chia-governor-triage-7b](https://savrn.com/models/chia-governor-triage-7b) [Venky](https://savrn.com/model-publishers/emailvenky) A LoRA adapter for Qwen2.5-Coder-7B-Instruct that predicts, from the code alone, whether a Verilog design change will fail its test bench before any simulator is run. It exists to sit in front of the expensive evaluation stage of an agentic hardware design loop. Simulation is slow and costly, and many agent proposals are simply wrong. This model triages them. Every frontier model tested carries the same wrong prior: that any edit to working code is probably a bug. That produces near-perfect recall and poor precision, so the gate throws away a large share of perfectly good designs. This adapter was trained on data containing verified-harmless edits alongside real faults, which attacks that… Open weights bsd-3-clause peft [View model](https://savrn.com/models/chia-governor-triage-7b) Model ### [classification](https://savrn.com/models/classification-2) [Gabriel Nascimento](https://savrn.com/model-publishers/gnascimentoeli) This is an experimental Tiny Transformer codebase for Classification. It keeps the tiny 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 lamb with a exponential schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 16,576 parameters 256 tokens [View model](https://savrn.com/models/classification-2) Model ### [classification-2023](https://savrn.com/models/classification-2023) [William Wilson](https://savrn.com/model-publishers/williamwilsonbef) This is an experimental Efficientformer codebase for Classification. 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 novograd with a cosine schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/classification-2023) Model ### [classification](https://savrn.com/models/classification-3) [Alyssa Gomez](https://savrn.com/model-publishers/alyssagoa) A research-oriented Swin T 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 rmsprop with a linear warmup schedule. These are starting values in the script, not evidence of a completed… Open weights bsd-3-clause 49,600 parameters 512 tokens [View model](https://savrn.com/models/classification-3) Model ### [classification](https://savrn.com/models/classification-4) [Kyle](https://savrn.com/model-publishers/kylemartineziah) Working implementation of Mixer for Classification using a base 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 lamb with a cosine schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/classification-4) Model ### [classification-experiments](https://savrn.com/models/classification-experiments) [C. Adeleke](https://savrn.com/model-publishers/luca-hcosta) This repository is a compact, custom PyTorch implementation of DeiT for Classification. The small 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 adafactor with a polynomial schedule. These… Open weights bsd-3-clause 24,832 parameters 512 tokens [View model](https://savrn.com/models/classification-experiments) Model ### [classification-proto](https://savrn.com/models/classification-proto) [Leandro.costa](https://savrn.com/model-publishers/costale90) This is an experimental Cnn Transformer codebase for Classification. It keeps the giant 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 novograd with a constant warmup schedule. These are starting values in the script, not evidence… Open weights bsd-3-clause 16,576 parameters 512 tokens [View model](https://savrn.com/models/classification-proto) Model ### [classification-quantized52](https://savrn.com/models/classification-quantized52) [Ssmiththomas](https://savrn.com/model-publishers/ssmiththomas) This repository is a compact, custom PyTorch implementation of Cnn Transformer for Classification. The small 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 constant warmup… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/classification-quantized52) Model ### [clip-classification-warmup](https://savrn.com/models/clip-classification-warmup) [Jason H. Lopez](https://savrn.com/model-publishers/llopezjason) A small CLIP implementation for Classification, packaged with an explicit configuration and an initialization checkpoint. The large 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 adamw with a exponential schedule. These are starting values in the script, not… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/clip-classification-warmup) Model ### [clip-contrastive-lab27](https://savrn.com/models/clip-contrastive-lab27) [Abdulrahman Alshehri](https://savrn.com/model-publishers/aalshehri52) A small CLIP implementation for Contrastive, packaged with an explicit configuration and an initialization checkpoint. The xlarge 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 sgd with a linear warmup schedule. These are starting values in the script, not… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/clip-contrastive-lab27) Model ### [clip-matching](https://savrn.com/models/clip-matching) [Marcus HO](https://savrn.com/model-publishers/marcusho0509) A small CLIP implementation for Matching, packaged with an explicit configuration and an initialization checkpoint. The xlarge 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 novograd with a polynomial schedule. These are starting values in the script, not… Open weights bsd-3-clause 16,576 parameters 128 tokens [View model](https://savrn.com/models/clip-matching) Model ### [clip-matching](https://savrn.com/models/clip-matching-4) [Myra](https://savrn.com/model-publishers/mykaur02) Open weights bsd-3-clause 24,832 parameters [View model](https://savrn.com/models/clip-matching-4) Model ### [clip-multitask](https://savrn.com/models/clip-multitask) [Daniil Kozlov](https://savrn.com/model-publishers/kkozlovdaniil) This is an experimental CLIP codebase for Multitask. It keeps the tiny 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 adam with a onecycle schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 49,600 parameters 128 tokens [View model](https://savrn.com/models/clip-multitask) Model ### [clip-retrieval21-2024](https://savrn.com/models/clip-retrieval21-2024) [Olivia K. Taylor](https://savrn.com/model-publishers/sakuramor6) This repository is a compact, custom PyTorch implementation of CLIP for Retrieval. The large 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 novograd with a constant warmup schedule. These… Open weights bsd-3-clause 33,088 parameters 512 tokens [View model](https://savrn.com/models/clip-retrieval21-2024) Model ### [cnn-transformer-generation](https://savrn.com/models/cnn-transformer-generation) [Karim Zahra-Rahman](https://savrn.com/model-publishers/kirillkir) This repository is a compact, custom PyTorch implementation of Cnn Transformer for Generation. The small 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 lamb with a polynomial schedule.… Open weights bsd-3-clause 16,576 parameters 256 tokens [View model](https://savrn.com/models/cnn-transformer-generation) Model ### [coca-baseline](https://savrn.com/models/coca-baseline) [Jonas Hartmann](https://savrn.com/model-publishers/jonashar) This is an experimental Coca codebase for Contrastive. It keeps the giant 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 rmsprop with a step schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/coca-baseline) Model ### [coca-classification](https://savrn.com/models/coca-classification) [Ingrid Weber](https://savrn.com/model-publishers/michaelvnguyen) A small Coca implementation for Classification, packaged with an explicit configuration and an initialization checkpoint. The base 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 novograd with a linear warmup schedule. These are starting values in the script… Open weights bsd-3-clause 49,600 parameters 512 tokens [View model](https://savrn.com/models/coca-classification) Model ### [coca-contrastive](https://savrn.com/models/coca-contrastive) [Thiago Almeida](https://savrn.com/model-publishers/thiagoalmei) This is an experimental Coca codebase for Contrastive. It keeps the tiny 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 novograd with a onecycle schedule. These are starting values in the script, not evidence of a completed run. For… Open weights bsd-3-clause 33,088 parameters 128 tokens [View model](https://savrn.com/models/coca-contrastive) Model ### [coca-matching](https://savrn.com/models/coca-matching) [Amit Mukherjee](https://savrn.com/model-publishers/ammukherjee) This repository is a compact, custom PyTorch implementation of Coca 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 sgd with a step schedule. These are starting values… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/coca-matching) Model ### [contrastive](https://savrn.com/models/contrastive-3) [James Thomas](https://savrn.com/model-publishers/jamesthomassen) A small Coca implementation for Contrastive, 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 evidence… Open weights bsd-3-clause 49,600 parameters 512 tokens [View model](https://savrn.com/models/contrastive-3) Model ### [contrastive](https://savrn.com/models/contrastive-4) [Thabo Bello](https://savrn.com/model-publishers/wuchunhung) This is an experimental Tiny Transformer codebase for Contrastive. It keeps the giant 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 linear warmup schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 24,832 parameters 512 tokens [View model](https://savrn.com/models/contrastive-4) Model ### [contrastive-aug](https://savrn.com/models/contrastive-aug) [Fahri Wulandari](https://savrn.com/model-publishers/fwula-ndari) Working implementation of Swin T for Contrastive using a giant 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 lamb with a exponential schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/contrastive-aug) Model ### [contrastive-beta](https://savrn.com/models/contrastive-beta) [Michael Becker](https://savrn.com/model-publishers/becker0125) This repository is a compact, custom PyTorch implementation of Dino for Contrastive. The tiny 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… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/contrastive-beta) Model ### [contrastive-test](https://savrn.com/models/contrastive-test) [Blrkumar1](https://savrn.com/model-publishers/blrkumar1) This is an experimental Mobilevit codebase for Contrastive. It keeps the large 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 adamw with a cosine schedule. These are starting values in the script, not evidence of a completed run.… Open weights bsd-3-clause 16,576 parameters 512 tokens [View model](https://savrn.com/models/contrastive-test) Model ### [contrastive-v1](https://savrn.com/models/contrastive-v1) [Theo Silva](https://savrn.com/model-publishers/chowdertheo) Open weights bsd-3-clause 24,832 parameters [View model](https://savrn.com/models/contrastive-v1) Model ### [contrastive37](https://savrn.com/models/contrastive37) [Anthony Bailey](https://savrn.com/model-publishers/anthonybbc) This is an experimental Swin T codebase for Contrastive. It keeps the tiny 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 lamb with a step schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 49,600 parameters 128 tokens [View model](https://savrn.com/models/contrastive37) Model ### [course-generation](https://savrn.com/models/course-generation) [Alberto G. Jimenez](https://savrn.com/model-publishers/albertojimenez) Working implementation of Perceiver for Generation using a small 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 polynomial schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 16,576 parameters 256 tokens [View model](https://savrn.com/models/course-generation) Model ### [course-generation](https://savrn.com/models/course-generation-2) [Madison Williams](https://savrn.com/model-publishers/williamsmadison) A small Albef implementation for Generation, packaged with an explicit configuration and an initialization checkpoint. The large 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 adafactor with a linear warmup schedule. These are starting values in the script, not… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/course-generation-2) Model ### [cs224n-matching](https://savrn.com/models/cs224n-matching) [Hu Siyuan](https://savrn.com/model-publishers/siyuanhu) A small Cnn Transformer 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 adam with a cosine schedule. These are starting values in the script, not… Open weights bsd-3-clause 16,576 parameters 512 tokens [View model](https://savrn.com/models/cs224n-matching) Model ### [cs231n-contrastive](https://savrn.com/models/cs231n-contrastive) [Hugo-Richard](https://savrn.com/model-publishers/hugorichardbury) Open weights bsd-3-clause 49,600 parameters [View model](https://savrn.com/models/cs231n-contrastive) Model ### [cs231n-generation](https://savrn.com/models/cs231n-generation) [Alice S. Gomes](https://savrn.com/model-publishers/alicegomes) Working implementation of Perceiver for Generation 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 constant warmup schedule. These are starting values in the script, not… Open weights bsd-3-clause 49,600 parameters 256 tokens [View model](https://savrn.com/models/cs231n-generation) Model ### [deit-contrastive](https://savrn.com/models/deit-contrastive) [Sophia Harris](https://savrn.com/model-publishers/vellorerobotics7768) This repository is a compact, custom PyTorch implementation of DeiT for Contrastive. The small 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 sgd with a exponential schedule. These are… Open weights bsd-3-clause 24,832 parameters 256 tokens [View model](https://savrn.com/models/deit-contrastive) Model ### [dino-baseline](https://savrn.com/models/dino-baseline) [Cheng Chen](https://savrn.com/model-publishers/ctchen5674) A research-oriented Dino prototype targeting Matching. The included large 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 lion with a constant warmup schedule. These are starting values in the script, not evidence of a completed run. For a… Open weights bsd-3-clause 16,576 parameters 128 tokens [View model](https://savrn.com/models/dino-baseline) Model ### [dino-generation28](https://savrn.com/models/dino-generation28) [Joshua Johnson](https://savrn.com/model-publishers/umassmechatronics) Working implementation of Dino for Generation using a small 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 step schedule. These are starting values in the script, not evidence of a completed… Open weights bsd-3-clause 16,576 parameters 128 tokens [View model](https://savrn.com/models/dino-generation28) Model ### [dissertation-contrastive-2024](https://savrn.com/models/dissertation-contrastive-2024) [Laura Garnier](https://savrn.com/model-publishers/lauragarnier) Working implementation of Mae for Contrastive using a nano 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 polynomial schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 33,088 parameters 128 tokens [View model](https://savrn.com/models/dissertation-contrastive-2024) Model ### [dl-retrieval](https://savrn.com/models/dl-retrieval) [Stefan Becker](https://savrn.com/model-publishers/stefanbeckerana) Working implementation of CLIP for Retrieval using a small 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 exponential schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 49,600 parameters 512 tokens [View model](https://savrn.com/models/dl-retrieval) Model ### [efficientformer-classification-exp](https://savrn.com/models/efficientformer-classification-exp) [Kacper Kowalczyk](https://savrn.com/model-publishers/kkowalczyk) Open weights bsd-3-clause 16,576 parameters [View model](https://savrn.com/models/efficientformer-classification-exp) Model ### [efficientformer-contrastive-prototype-2023](https://savrn.com/models/efficientformer-contrastive-prototype-2023) [Nikhilvnv](https://savrn.com/model-publishers/nikhilvnv) A small Efficientformer implementation for Contrastive, packaged with an explicit configuration and an initialization checkpoint. The nano 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 novograd with a step schedule. These are starting values in the script, not… Open weights bsd-3-clause 49,600 parameters 512 tokens [View model](https://savrn.com/models/efficientformer-contrastive-prototype-2023) Model ### [efficientformer-finetuned](https://savrn.com/models/efficientformer-finetuned) [Hassanalshehri](https://savrn.com/model-publishers/hassanalshehri) A small Efficientformer implementation for Retrieval, packaged with an explicit configuration and an initialization checkpoint. The tiny 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 lamb with a polynomial schedule. These are starting values in the script, not… Open weights bsd-3-clause 16,576 parameters 256 tokens [View model](https://savrn.com/models/efficientformer-finetuned) Model ### [experiment-classification](https://savrn.com/models/experiment-classification) [Yang](https://savrn.com/model-publishers/wangyang92) A small Coca implementation for Classification, packaged with an explicit configuration and an initialization checkpoint. The tiny 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 adamw with a polynomial schedule. These are starting values in the script, not… Open weights bsd-3-clause 33,088 parameters 512 tokens [View model](https://savrn.com/models/experiment-classification) Model ### [flamingo-classification-proto](https://savrn.com/models/flamingo-classification-proto) [Tyler Jackson](https://savrn.com/model-publishers/tylerjtj4205) This repository is a compact, custom PyTorch implementation of Flamingo 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 lamb with a exponential schedule. These… Open weights bsd-3-clause 33,088 parameters 256 tokens [View model](https://savrn.com/models/flamingo-classification-proto) Model ### [generation-best](https://savrn.com/models/generation-best) [Edwin W. Gunawan](https://savrn.com/model-publishers/etgu-nawan) This repository is a compact, custom PyTorch implementation of Poolformer for Generation. The large 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 adafactor with a step schedule. These are… Open weights bsd-3-clause 16,576 parameters 512 tokens [View model](https://savrn.com/models/generation-best) Model ### [generation33-2024](https://savrn.com/models/generation33-2024) [Ashley Smith](https://savrn.com/model-publishers/tidepoo-lashley) This is an experimental Flamingo codebase for Generation. 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 rmsprop with a constant warmup schedule. These are starting values in the script, not evidence of a… Open weights bsd-3-clause 33,088 parameters 128 tokens [View model](https://savrn.com/models/generation33-2024) ## Questions ### Can I use BSD 3-Clause License models commercially? Yes. The BSD 3-Clause License is permissive. It permits commercial use and redistribution with the copyright notice, and forbids using the authors' names to endorse derived products without permission. ### Which BSD 3-Clause License models are most downloaded? By monthly downloads reported by the Hugging Face Hub: blip-image-captioning-base (1.3M); ast-finetuned-audioset-10-10-0.4593 (1.3M); blip-image-captioning-large (539.2k). ## Other Licenses - [apache-2.0](https://savrn.com/models/licenses/apache-2-0) 3344 - [mit](https://savrn.com/models/licenses/mit) 1319 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 213 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 164 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) 55 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 40 - [unknown](https://savrn.com/models/licenses/unknown) 33 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 28 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 - [gpl-3.0](https://savrn.com/models/licenses/gpl-3-0) 20 [See all](https://savrn.com/models/licenses)