# Open-Weight Models Under Creative Commo…rcial-ShareAlike 4.0 Source: https://savrn.com/models/licenses/cc-by-nc-sa-4-0 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 Creative Commons Attribution-NonCommercial-ShareAlike 4.0 56 open-weight models released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 in the SAVRN Model Hub, with Rishanth Rajendhran, Devon Yanitski and audEERING GmbH publishing the most. 56Models 36Publishers 39M to 9BParameter range 1Licenses Not without separate permissionCommercial use ## What Creative Commons Attribution-NonCommercial-ShareAlike 4.0 Allows CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission. ## SAVRN's Take Start with the NonCommercial clause. Creative Commons Attribution-NonCommercial-ShareAlike 4.0 lets you share and adapt a model with credit, and any adaptation has to carry the same license, so a released fine-tune goes back out under CC BY-NC-SA 4.0. Commercial use is not permitted without separate permission. An internal research team can live with that. Anyone planning to serve it to paying customers or fold it into a product is stopped at the door until the rights holder says otherwise. Hardware is never the constraint. Sixteen models sit under this license on our hub, and the largest of the most downloaded, E-MIMIC's 783M-parameter inclusively-reformulation-it5, needs 1.9 GB at 16-bit. Microsoft's layoutlmv3-base, 125M parameters with a 514-token context, wants 0.3 GB. The Index puts the cheapest host at one MI300X for $1.85 an hour, so the real choice is the license, not the card. audEERING GmbH leads with three models, all audio classifiers, then E-MIMIC and the Stanford Tabular and Relational (STAR) Project at two each, with Microsoft, Babelscape, Vennify AI, IBM Research and the Music Technology Group at Universitat Pompeu Fabra at one apiece. Downloads stack at the top: inclusively-reformulation-it5 draws 3,584,790 a month, audEERING's 318M-parameter wav2vec2 age and gender classifier 2,477,432, and layoutlmv3-base 1,148,823. Read the publisher's card first. audEERING marks its 165M-parameter wav2vec2 emotion model as research only and offers a commercial license on a model trained on more data, which is how NonCommercial works in practice. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [finbert](https://savrn.com/models/finbert) | Prosus AI | 109M | cc-by-nc-sa-4.0 | 3.9M | 1x MI300X, $1.85/hr | | [wav2vec2-large-robust-24-ft-age-gender](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender) | audEERING GmbH | 318M | cc-by-nc-sa-4.0 | 2.2M | 1x MI300X, $1.85/hr | | [inclusively-reformulation-it5](https://savrn.com/models/inclusively-reformulation-it5) | E-MIMIC | 783M | cc-by-nc-sa-4.0 | 2.2M | 1x MI300X, $1.85/hr | | [layoutlmv3-base](https://savrn.com/models/layoutlmv3-base) | Microsoft | 125M | cc-by-nc-sa-4.0 | 1.1M | 1x MI300X, $1.85/hr | | [splade-cocondenser-selfdistil](https://savrn.com/models/splade-cocondenser-selfdistil) | NAVER | — | cc-by-nc-sa-4.0 | 1.1M | — | | [wav2vec2-large-robust-12-ft-emotion-msp-dim](https://savrn.com/models/wav2vec2-large-robust-12-ft-emotion-msp-dim) | audEERING GmbH | 165M | cc-by-nc-sa-4.0 | 804.8k | 1x MI300X, $1.85/hr | | [wikineural-multilingual-ner](https://savrn.com/models/wikineural-multilingual-ner) | Babelscape | 177M | cc-by-nc-sa-4.0 | 677.1k | 1x MI300X, $1.85/hr | | [inclusively-classification](https://savrn.com/models/inclusively-classification) | E-MIMIC | 111M | cc-by-nc-sa-4.0 | 552.2k | 1x MI300X, $1.85/hr | | [wav2vec2-large-robust-6-ft-age-gender](https://savrn.com/models/wav2vec2-large-robust-6-ft-age-gender) | audEERING GmbH | 91M | cc-by-nc-sa-4.0 | 167.3k | 1x MI300X, $1.85/hr | | [t5-base-grammar-correction](https://savrn.com/models/t5-base-grammar-correction) | Vennify AI | — | cc-by-nc-sa-4.0 | 114.3k | — | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) | 9 | | [Devon Yanitski](https://savrn.com/model-publishers/devon7y) | 3 | | [audEERING GmbH](https://savrn.com/model-publishers/audeering) | 3 | | [AbstractPhila](https://savrn.com/model-publishers/abstractphil) | 3 | | [Xuandong Liang](https://savrn.com/model-publishers/xunden) | 2 | | [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) | 2 | ## All 56 Models Model · Text classification ### [finbert](https://savrn.com/models/finbert) [Prosus AI](https://savrn.com/model-publishers/prosusai) FinBERT is a pre-trained NLP model to analyze sentiment of financial text. It is built by further training the BERT language model in the finance domain, using a large financial corpus and thereby fine-tuning it for financial sentiment classification. Financial PhraseBank by Malo et al. (2014) is used for fine-tuning. For more details, please see the paper FinBERT: Financial Sentiment Analysis with Pre-trained Language Models and our related blog post on Medium. The model will give softmax outputs for three labels: positive, negative or neutral. To get the scores for all three labels, pass topk=None to the classifier. This model was trained using the Financial PhraseBank dataset: The… Open weights cc-by-nc-sa-4.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/finbert) Model · Audio classification ### [wav2vec2-large-robust-24-ft-age-gender](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender) [audEERING GmbH](https://savrn.com/model-publishers/audeering) The model expects a raw audio signal as input and outputs predictions for age in a range of approximately 0...1 (0...100 years) and gender expressing the probababilty for being child, female, or male. In addition, it also provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust Timit and For this version of the model we trained all 24 transformer layers. An ONNX export of the model is available from Further details are given in the associated paper and tutorial. Open weights cc-by-nc-sa-4.0 318M parameters transformers [View model](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender) Model ### [inclusively-reformulation-it5](https://savrn.com/models/inclusively-reformulation-it5) [E-MIMIC](https://savrn.com/model-publishers/e-mimic) This model is an Italian sequence-to-sequence model fine-tuned from the IT5-large for the task of inclusive language rewriting. It has been trained to analyze and rewrite sentences in Italian to make them more inclusive (if needed). For example, the sentence I professori devono essere preparati (The professors must be prepared) is rewritten as Il personale docente deve essere preparato (The teaching staff must be prepared). The model has been trained on a dataset containing a total of 4705 pairs of sentences, each pair containing an inclusive and a non-inclusive sentence. The dataset has been split as follows: We also leverage a small set of synthetic data (generated using a set of rules)… Open weights cc-by-nc-sa-4.0 783M parameters transformers [View model](https://savrn.com/models/inclusively-reformulation-it5) Model ### [layoutlmv3-base](https://savrn.com/models/layoutlmv3-base) [Microsoft](https://savrn.com/model-publishers/microsoft) LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks such as document image classification and document layout analysis. Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei, ACM Multimedia 2022. If you find LayoutLM useful in your research, please cite the following paper: The content of this project itself is licensed under the… Open weights cc-by-nc-sa-4.0 125M parameters 514 tokens transformers [View model](https://savrn.com/models/layoutlmv3-base) Model · Feature extraction ### [splade-cocondenser-selfdistil](https://savrn.com/models/splade-cocondenser-selfdistil) [NAVER](https://savrn.com/model-publishers/naver) SPLADE model for passage retrieval. For additional details, please visit: This is a SPLADE Sparse Encoder model. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval. First install the Sentence Transformers library: Then you can load this model and run inference. If you use our checkpoint, please cite our work Open weights cc-by-nc-sa-4.0 512 tokens sentence-transformers [View model](https://savrn.com/models/splade-cocondenser-selfdistil) Model · Audio classification ### [wav2vec2-large-robust-12-ft-emotion-msp-dim](https://savrn.com/models/wav2vec2-large-robust-12-ft-emotion-msp-dim) [audEERING GmbH](https://savrn.com/model-publishers/audeering) Please note that this model is for research purpose only. A commercial license for a model that has been trained on much more data can be acquired with audEERING. The model expects a raw audio signal as input, and outputs predictions for arousal, dominance and valence in a range of approximately 0...1. In addition, it provides the pooled states of the last transformer layer. The model was created by fine-tuning The model was pruned from 24 to 12 transformer layers before fine-tuning. An ONNX export of the model is available from doi:10.5281/zenodo.6221127. Further details are given in the associated paper and tutorial. Open weights cc-by-nc-sa-4.0 165M parameters transformers [View model](https://savrn.com/models/wav2vec2-large-robust-12-ft-emotion-msp-dim) Model · Token classification ### [wikineural-multilingual-ner](https://savrn.com/models/wikineural-multilingual-ner) [Babelscape](https://savrn.com/model-publishers/babelscape) This is the model card for the EMNLP 2021 paper WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER. We fine-tuned a multilingual language model (mBERT) for 3 epochs on our WikiNEuRal dataset for Named Entity Recognition (NER). The resulting multilingual NER model supports the 9 languages covered by WikiNEuRal (de, en, es, fr, it, nl, pl, pt, ru), and it was trained on all 9 languages jointly. If you use the model, please reference this work in your paper: The original repository for the paper can be found at https://github.com/Babelscape/wikineural. You can use this model with Transformers pipeline for NER. This model is trained on WikiNEuRal, a… Open weights cc-by-nc-sa-4.0 177M parameters 512 tokens transformers [View model](https://savrn.com/models/wikineural-multilingual-ner) Model · Text classification ### [inclusively-classification](https://savrn.com/models/inclusively-classification) [E-MIMIC](https://savrn.com/model-publishers/e-mimic) This model is an Italian classification model fine-tuned from the Italian BERT model for the classification of inclusive language in Italian. It has been trained to detect three classes: - inclusive: the sentence is inclusive (e.g. "Il personale docente e non docente") - notinclusive: the sentence is not inclusive (e.g. "I professori") - notpertinent: the sentence is not pertinent to the task (e.g. "La scuola è chiusa") The model has been trained on a dataset containing: - 8580 training sentences - 1073 validation sentences - 1072 test sentences The data collection has been manually annotated by experts in the field of inclusive language (dataset is not publicly available yet). The model… Open weights cc-by-nc-sa-4.0 111M parameters 512 tokens transformers [View model](https://savrn.com/models/inclusively-classification) Model · Audio classification ### [wav2vec2-large-robust-6-ft-age-gender](https://savrn.com/models/wav2vec2-large-robust-6-ft-age-gender) [audEERING GmbH](https://savrn.com/model-publishers/audeering) The model expects a raw audio signal as input and outputs predictions for age in a range of approximately 0...1 (0...100 years) and gender expressing the probababilty for being child, female, or male. In addition, it also provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust Timit and For this version of the model we only trained the first six transformer layers. An ONNX export of the model is available from Further details are given in the associated paper and tutorial. Open weights cc-by-nc-sa-4.0 91M parameters transformers [View model](https://savrn.com/models/wav2vec2-large-robust-6-ft-age-gender) Model ### [t5-base-grammar-correction](https://savrn.com/models/t5-base-grammar-correction) [Vennify AI](https://savrn.com/model-publishers/vennify) This model generates a revised version of inputted text with the goal of containing fewer grammatical errors. It was trained with Happy Transformer using a dataset called JFLEG. Here's a full article on how to train a similar model. pip install happytransformer Open weights cc-by-nc-sa-4.0 transformers [View model](https://savrn.com/models/t5-base-grammar-correction) Model · Time series forecasting ### [patchtst-fm-r1](https://savrn.com/models/patchtst-fm-r1) [IBM Research](https://savrn.com/model-publishers/ibm-research) This model card is for the non-commercial, research version of PatchTST-FM-r1. Please also check-out the Apache-2.0 licensed IBM Granite version. PatchTST was originally released prior to the interest in creating pre-trained, zero-shot time series foundation models that were capable of state-of-the-art performance on out of sample datasets. PatchTST-FM (patched time-series transformer-based foundation model) essentially has the architectural simplicity of PatchTST, but differs in some crucial ways. Coupled with a revised training strategy and a significantly larger training corpus, we are able to train a model that achieves state-of-the-art results on GiftEval. The architecture incorporates… Open weights cc-by-nc-sa-4.0 258M parameters [View model](https://savrn.com/models/patchtst-fm-r1) Model · Audio classification ### [discogs-maest-10s-pw-129e](https://savrn.com/models/discogs-maest-10s-pw-129e) [Music Technology Group (Universitat Pompeu Fabra)](https://savrn.com/model-publishers/mtg-upf) MAEST is a family of Transformer models based on PASST and focused on music analysis applications. The MAEST models are also available for inference in the Essentia library and for inference and training in the official repository. You can try the MAEST interactive demo on replicate. MAEST is a music audio representation model pre-trained on the task of music style classification. According to the evaluation reported in the original paper, it reports good performance in several downstream music analysis tasks. The MAEST models can make predictions for a taxonomy of 400 music styles derived from the public metadata of Discogs. The MAEST models have reported good performance in downstream… Open weights cc-by-nc-sa-4.0 86M parameters transformers [View model](https://savrn.com/models/discogs-maest-10s-pw-129e) Model · Summarization ### [ptt5-base-summ-xlsum](https://savrn.com/models/ptt5-base-summ-xlsum) [Recogna NLP](https://savrn.com/model-publishers/recogna-nlp) PTT5 Summ is a fine-tuned PTT5 model to perform Abstractive Summarization in Brazilian Portuguese texts. This model was fine-tuned on the datasets: RecognaSumm, WikiLingua, XL-Sum, TeMário.pdf) and CSTNews. For further information, please go to PTT5 Summ repository. author="Paiola, Pedro H. and de Rosa, Gustavo H. and Papa, Jo{\~a}o P.", editor="Xavier-Junior, Jo{\~a}o Carlos and Rios, Ricardo Ara{\'u}jo", title="Deep Learning-Based Abstractive Summarization for Brazilian Portuguese Texts", booktitle="BRACIS 2022: Intelligent Systems", year="2022", publisher="Springer International Publishing", address="Cham", pages="479--493", isbn="978-3-031-21689-3"} This model was fine-tuned using the… Open weights cc-by-nc-sa-4.0 223M parameters transformers [View model](https://savrn.com/models/ptt5-base-summ-xlsum) Model · Text classification ### [IdeaLens-Qwen3.5-9B](https://savrn.com/models/idealens-qwen3-5-9b) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-Qwen3.5-9B is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o scores.jsonl… Open weights cc-by-nc-sa-4.0 7.9B parameters 262,144 tokens transformers [View model](https://savrn.com/models/idealens-qwen3-5-9b) Model · Tabular classification ### [rt-plurel](https://savrn.com/models/rt-plurel) [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) RT-PluRel is a Relational Transformer checkpoint pair for in-context / few-shot entity prediction over multi-table relational databases (no per-task gradient training). Same architecture and file layout as stanford-star/rt-j — drop-in replacement. Architecture: ~85.6M blocks, dmodel 512, 8 heads, dff 2048 · text columns embedded with all-MiniLM-L12-v2 (dtext 384). Each folder contains model.safetensors (weights) and config.json (dims + text-embedding model). The paper/ subdirectory preserves the earlier RT-PluRel release:.pt checkpoints (12 blocks, dmodel 256, dff 1024) pretrained on synthetic relational databases generated by PluRel, plus the continued-pretraining and fine-tuned RelBench… Open weights cc-by-nc-sa-4.0 86M parameters pytorch [View model](https://savrn.com/models/rt-plurel) Model · Fill mask ### [logun-base](https://savrn.com/models/logun-base) [Heitorrosa](https://savrn.com/model-publishers/heitorrosa) This model is a fine-tuned version of Itau-Unibanco/NorBERTo-base on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 2 - evalbatchsize: 4 - gradientaccumulationsteps: 16 - totaltrainbatchsize: 32 - lrschedulertype: linear - lrschedulerwarmupsteps: 500 - numepochs: 1.5 - mixedprecisiontraining: Native AMP - PEFT 0.20.0 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.0.0 - Tokenizers 0.23.1 Open weights cc-by-nc-sa-4.0 150M parameters 8,192 tokens peft [View model](https://savrn.com/models/logun-base) Model · Speech recognition ### [tiny-audio](https://savrn.com/models/tiny-audio) [Alex Kroman](https://savrn.com/model-publishers/mazesmazes) A tiny, hackable, open-source speech LLM. It transcribes English with punctuation, capitalization, word timestamps, and speaker labels. Built and trained with Tiny Audio. Tiny Audio connects a frozen, pretrained speech encoder to a pretrained LLM with a small trainable The published model pairs the non-causal Granite Speech 5.0 470M encoder (kept frozen) with the Qwen3-0.6B decoder. The MLP projector maps encoder frames into the decoder's embedding space; it is the only part trained from scratch, and the whole decoder is fine-tuned alongside it: ~604M trained parameters (596M decoder, 8.4M projector). The encoder, projector, and decoder are each swappable from config in the training repo.… Open weights cc-by-nc-sa-4.0 604M parameters 40,960 tokens transformers [View model](https://savrn.com/models/tiny-audio) Model · Text generation ### [hpc-assistant-qwen3-4b](https://savrn.com/models/hpc-assistant-qwen3-4b) [Vaibhav Kailash Mangroliya](https://savrn.com/model-publishers/vaibhavkkm) A fine-tuned Qwen/Qwen3-4B-Instruct-2507 that answers HPC questions: Slurm job scripts, GPUs, modules, storage, and access to EuroHPC systems and the European AI Factories. It works best with retrieved documentation excerpts in the prompt. This release is a full merged model (bf16 safetensors), built in four stages: 1. Logit distillation (round 12a). The student learns the full next-token distribution of Qwen3-Next-80B-A3B-Instruct (top-20 probabilities at every answer token) on 46,717 verified question–answer pairs. LoRA rank 32. Merged. 2. On-policy distillation from Qwen3-Next (round 12e). The stage-1 model answers the training questions itself; 14,514 of its own answers are scored token… Open weights cc-by-nc-sa-4.0 4B parameters 262,144 tokens transformers [View model](https://savrn.com/models/hpc-assistant-qwen3-4b) Model · Tabular classification ### [rt-j](https://savrn.com/models/rt-j) [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) Open weights cc-by-nc-sa-4.0 86M parameters [View model](https://savrn.com/models/rt-j) Model ### [PlatYi-34B-200k-Q-FastChat-GGUF](https://savrn.com/models/platyi-34b-200k-q-fastchat-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) static quants of https://huggingface.co/kyujinpy/PlatYi-34B-200k-Q-FastChat For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/PlatYi-34B-200k-Q-FastChat-i1-GGUF 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 quant And here are Artefact2's thoughts on the matter… Open weights cc-by-nc-sa-4.0 transformers [View model](https://savrn.com/models/platyi-34b-200k-q-fastchat-gguf) Model · Image segmentation ### [DART-Seg](https://savrn.com/models/dart-seg) [Swarna](https://savrn.com/model-publishers/koushik45048545309) Text-prompted 3D CT segmentation. Name a structure, get its mask. 286 anatomical structures and lesions, 39M parameters, trained from scratch. ONLY PROMPT FOR THE STRUCTURES YOU NEED. Prompting for unnecessary or anatomically absent structures may cause hallucinations and false-positive segmentations. After inference, DART-Seg may produce fragments. Use the below postprocessing to fix that. Quote prompts and paths that contain spaces, e.g. --prompts "left kidney" or --image "my scan.nii.gz". Python API (run from inside the downloaded folder so dartseg.py is importable): - Residual 3D U-Net; each prompt's text embedding attends to image features and produces its mask. All prompts share one… Open weights cc-by-nc-sa-4.0 39M parameters pytorch [View model](https://savrn.com/models/dart-seg) Model · Speech recognition ### [koelsch-wav2vec2-ipa](https://savrn.com/models/koelsch-wav2vec2-ipa) [Chem](https://savrn.com/model-publishers/vatho) IPA phoneme recognition for Kölsch (Ripuarian German, Cologne). Fine-tuned from facebook/wav2vec2-xls-r-300m with a CTC head over a 48-symbol IPA inventory. This is also the forced-alignment model. Its frame-level CTC posteriors drive torchaudio.functional.forcedalign to produce Praat TextGrids with word and phone tiers — see notebook 9 in the repository. Trained during the CIF Tandem Fellowship at IfL-Phonetik, University of Cologne, on Alles Kölsch (Bhatt & Lindlar 1998) — 4,670 utterances, 4.5 hours of spontaneous Cologne dialect speech from 105 speakers aged 10–88 across 49 neighbourhoods. Kölsch is Ripuarian German. It has no public speech dataset and no standardised spelling: 94.1 %… Open weights cc-by-nc-sa-4.0 315M parameters transformers [View model](https://savrn.com/models/koelsch-wav2vec2-ipa) Model · Text classification ### [IdeaLens-ModernBERT-L-NoParaphrase](https://savrn.com/models/idealens-modernbert-l-noparaphrase) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-ModernBERT-L-NoParaphrase is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o… Open weights cc-by-nc-sa-4.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/idealens-modernbert-l-noparaphrase) Model · Image segmentation ### [MicroStructFormer](https://savrn.com/models/microstructformer) [Nianqi Deng](https://savrn.com/model-publishers/dnq2025) MicroStructFormer is a high-capacity Mask2Former model built on a Swin-Large backbone, designed for the semantic segmentation of ultrastructures in Electron Microscopy (EM) images. This model has been trained to accurately segment the following critical ultrastructural elements: Note: While the model architecture theoretically supports axon and myelin segmentation, this specific release is optimized and calibrated for the classes listed below due to dataset annotations. You can use this model easily via the transformers library. This Hugging Face model repository is associated with the following bioRxiv preprint: These model weights and associated architectures are provided for… Open weights cc-by-nc-sa-4.0 216M parameters transformers [View model](https://savrn.com/models/microstructformer) Model ### [my-private-model](https://savrn.com/models/my-private-model) [Jeffery Anderson](https://savrn.com/model-publishers/theinfamousbanana) This repository contains randomly selected AI models available to the public under the CC-BY-NC-SA 4.0 International license. Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/my-private-model) Model · Text classification ### [IdeaLens-Qwen3.5-9B-PerItem](https://savrn.com/models/idealens-qwen3-5-9b-peritem) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-Qwen3.5-9B-PerItem is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o… Open weights cc-by-nc-sa-4.0 7.9B parameters 262,144 tokens transformers [View model](https://savrn.com/models/idealens-qwen3-5-9b-peritem) Model · Text classification ### [IdeaLens-ModernBERT-L](https://savrn.com/models/idealens-modernbert-l) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-ModernBERT-L is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o scores.jsonl… Open weights cc-by-nc-sa-4.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/idealens-modernbert-l) Model · Text classification ### [IdeaLens-ModernBERT-L-PerItem](https://savrn.com/models/idealens-modernbert-l-peritem) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-ModernBERT-L-PerItem is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o… Open weights cc-by-nc-sa-4.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/idealens-modernbert-l-peritem) Model · Text classification ### [IdeaLens-ModernBERT-L-RolesOnly](https://savrn.com/models/idealens-modernbert-l-rolesonly) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-ModernBERT-L-RolesOnly is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o… Open weights cc-by-nc-sa-4.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/idealens-modernbert-l-rolesonly) Model · Text classification ### [ProseLens-ModernBERT-L](https://savrn.com/models/proselens-modernbert-l) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) ProseLens-ModernBERT-L is a prose-level detector: it reads the document itself and judges who wrote the words. It is the ModernBERT counterpart of ProseLens and the comparison point for the idea-level detectors. Score documents directly; no outline is needed. The idealens package (PyPI) applies this model and the thresholds in this repo: Input is JSONL with a text field per document. thresholds.json holds this model's cuts at 0.1%, 0.5%, 1%, 2% and 5% false-positive rates, fitted on the 80,000 human documents of WildOutlines' calibration split: one global cut per rate, plus per-format cuts. The package applies them. A cut fitted for one model does not transfer to another model's scores. For… Open weights cc-by-nc-sa-4.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/proselens-modernbert-l) Model ### [alephllm-mini-beatrix-training](https://savrn.com/models/alephllm-mini-beatrix-training) [AbstractPhila](https://savrn.com/model-publishers/abstractphil) Live training ground for AlephLLM: signed-address (aleph) language models. Code, presets, trainer, and the full test array live in the source repo — github.com/AbstractEyes/alephllm (pip install git+https://github.com/AbstractEyes/alephllm, package geolip.alephllm). This repo holds what training produces, one prefix - mini-beatrix-3 — COMPLETE (2026-10-05; started 2026-09-20, relaunched 2026-09-27 on the engineered form and 2026-09-28 on amoe-lora 0.2.11). The v3 craft: 32 blocks, d 1024, 16 heads, context 4096, byte vocabulary with the trigram byte embedding, about 376M parameters. Every block carries a CausalSplatHUB (four address constellations, K 64 at D 128, the exact chunked scan at… Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/alephllm-mini-beatrix-training) Model ### [alephllm-nano-beatrix-training](https://savrn.com/models/alephllm-nano-beatrix-training) [AbstractPhila](https://savrn.com/model-publishers/abstractphil) Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/alephllm-nano-beatrix-training) Model · Text generation ### [alephllm-nano-castor-pollux](https://savrn.com/models/alephllm-nano-castor-pollux) [AbstractPhila](https://savrn.com/model-publishers/abstractphil) Open weights cc-by-nc-sa-4.0 transformers [View model](https://savrn.com/models/alephllm-nano-castor-pollux) Model ### [anode-models](https://savrn.com/models/anode-models) [Moh Hasbi Alfarizi](https://savrn.com/model-publishers/peanut2butter9) Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/anode-models) Model · Image classification ### [CIRCLE](https://savrn.com/models/circle) [Wangjiayu](https://savrn.com/model-publishers/uii-open-source) Access requested at publisher cc-by-nc-sa-4.0 transformers [View model](https://savrn.com/models/circle) Model · Text to image ### [diablo-huma-lora](https://savrn.com/models/diablo-huma-lora) [COLUMBA PARRAGA ERICK DAVID](https://savrn.com/model-publishers/asdhell096) Adaptador LoRA (Low-Rank Adaptation) entrenado para generar imágenes del traje emblemático del Diablo Huma de Pujilí (patrimonio cultural inmaterial del Ecuador), como parte de un trabajo de titulación sobre preservación digital del patrimonio con IA. En este repositorio se incluye un cuaderno listo para generar imágenes con el adaptador: Cómo usarlo: descárgalo y súbelo a Google Colab (Archivo → Subir cuaderno), activa GPU (Entorno de ejecución → Cambiar tipo de entorno → T4) y ejecuta las celdas. Como alternativa confiable, el modelo también se puede usar en ComfyUI. - Palabra de activación (trigger): d14bl0huma Compatible con ComfyUI, AI-Toolkit (Ostris) y diffusers (loadloraweights).… Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/diablo-huma-lora) Model · Video text to text ### [EventLens-4B](https://savrn.com/models/eventlens-4b) [Guowen Zhang](https://savrn.com/model-publishers/lostgreen) EventLens-4B is a video-language model developed through event-structure reinforcement learning and multi-teacher on-policy distillation (MT-OPD). Built on Qwen3-VL-4B-Instruct, it learns to recognize event boundaries, progression, and relations, alongside temporal grounding and video question answering. The model is part of EventLens: Event-Structure Reinforcement Learning for Video Understanding, developed by AIM3 Lab, Renmin University of China, and Kling AI. Selected results reported in the EventLens paper, compared with the corresponding pretrained backbone under the shared 256-frame protocol. QVHighlights, ActivityNet, and Charades-STA use mIoU. E.T. Bench and VinoGround use their… Open weights cc-by-nc-sa-4.0 4.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/eventlens-4b) Model · Video text to text ### [EventLens-8B](https://savrn.com/models/eventlens-8b) [Guowen Zhang](https://savrn.com/model-publishers/lostgreen) EventLens-8B is a video-language model developed through event-structure reinforcement learning and multi-teacher on-policy distillation (MT-OPD). Built on Qwen3-VL-8B-Instruct, it learns to recognize event boundaries, progression, and relations, alongside temporal grounding and video question answering. The model is part of EventLens: Event-Structure Reinforcement Learning for Video Understanding, developed by AIM3 Lab, Renmin University of China, and Kling AI. Selected results reported in the EventLens paper, compared with the corresponding pretrained backbone under the shared 256-frame protocol. QVHighlights, ActivityNet, and Charades-STA use mIoU. E.T. Bench and VinoGround use their… Open weights cc-by-nc-sa-4.0 8.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/eventlens-8b) Model ### [finbert-GGUF](https://savrn.com/models/finbert-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) static quants of https://huggingface.co/ProsusAI/finbert 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 quant And here… Open weights cc-by-nc-sa-4.0 transformers [View model](https://savrn.com/models/finbert-gguf) Model ### [grammar-de](https://savrn.com/models/grammar-de) [Kotoshu](https://savrn.com/model-publishers/kotoshu) Fully local German grammar correction model for the ≤250 MB weight class (run anywhere, CPU real-time, no network). iterative apply-and-retag decoding, on a microsoft/mdeberta-v3-base encoder. byte-fallback), pruned by weight-truth-verified remap — int8 ONNX gate, 48.5% yield) from typed corruption packs (articles, verb agreement, V2, separable verbs, case government); two-stage differential-LR schedule, byte-identical with HF) + ONNX Runtime; inference is milliseconds per sentence on a laptop CPU. German has no public GEC benchmark we can license for automated scoring, so we report a held-out judge study instead: This is a deliberately conservative corrector: it almost never invents… Open weights cc-by-nc-sa-4.0 onnx [View model](https://savrn.com/models/grammar-de) Model ### [grammar-en](https://savrn.com/models/grammar-en) [Kotoshu](https://savrn.com/model-publishers/kotoshu) An 85.8 MB int8 ONNX token tagger that detects and corrects grammatical errors fully locally — no data leaves the machine. GECToR architecture (Omelianchuk et al. 2020): distilroberta encoder, 5,000-label closed vocabulary ($KEEP / $REPLACE / $APPEND / $DELETE / $TRANSFORM / $MERGE), iterative apply-and-retag decoding (4 rounds). Scored with the official M2 scorer, noalt gold, --maxunchangedwords 2, 4-round iterative decode: 2.9x LanguageTool; runs in ~6 ms/sentence on a laptop CPU through onnxruntime. labels.json (id -> label map — do not rebuild), vocab.json + merges.txt (distilroberta byte-level BPE). label vocab = top 5,000 from the training mix. real-time (~6 ms/sentence), 85.8 MB int8… Open weights cc-by-nc-sa-4.0 onnxruntime [View model](https://savrn.com/models/grammar-en) Model ### [HTR_model_Finetued_Arams-28k](https://savrn.com/models/htr-model-finetued-arams-28k) [Archatext](https://savrn.com/model-publishers/archatext) arabic - handwritten-text-recognition - htr - ocr - historical-manuscripts - kraken libraryname: kraken arman-kraken-ocr is a Kraken OCR/HTR model for line-level recognition of handwritten Arabic manuscripts. The model is based on the Muharaf-trained Kraken checkpoint muharafrecbest.mlmodel and was subsequently fine-tuned on the ArMan dataset for historical Arabic manuscript recognition. This checkpoint is a fine-tuned derivative of the Arabic HTR model trained on the Muharaf Corpus: The model was fine-tuned on ArMan as part of our work on historical Arabic manuscript HTR and the AraMS-28k dataset. If you use AraMS-28k in your research, please cite: If you use RefLAM or its annotation… Open weights cc-by-nc-sa-4.0 kraken [View model](https://savrn.com/models/htr-model-finetued-arams-28k) Model ### [IdeaLens-LogisticClassifier](https://savrn.com/models/idealens-logisticclassifier) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-LogisticClassifier is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o… Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/idealens-logisticclassifier) Model ### [IdeaLens-LogisticClassifier-PerItem](https://savrn.com/models/idealens-logisticclassifier-peritem) [Rishanth Rajendhran](https://savrn.com/model-publishers/rishanthrajendhran) IdeaLens-LogisticClassifier-PerItem is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data. The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo. Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl… Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/idealens-logisticclassifier-peritem) Model ### [LIBE](https://savrn.com/models/libe) [Ca' Foscari NLP](https://savrn.com/model-publishers/cafoscari-nlp) basemodel: - sentence-transformers/LaBSE - language-identification - langID - sentence-embedding - similarity-search - low-resource - low-resource-languages Open weights cc-by-nc-sa-4.0 471M parameters 512 tokens [View model](https://savrn.com/models/libe) Model · Image and text to text ### [Lite-OmniJev](https://savrn.com/models/lite-omnijev) [Wang](https://savrn.com/model-publishers/chinzhu) 冻结 Gemma 4 E4B 基座 + 决策 LoRA，每题一次前向读出全部选项概率。 支持 Choice（2–20项）、Score（2–10级）、yes/no，覆盖文本、图像、截图、音频与视频。 API直接返回答案概率、置信度和结构化判断。 MMAU音频路由基座方案采用65.9%的实测结果；默认部署脚本采用全模态adapter。 真实模型工作台通过三类判断、图像/截图/音频/视频、cURL重放及错误恢复验证。 GGUF三档在20个公开文本案例上均与参考选答20/20一致，截图、音频和视频运行探针全部成功。 环境：Linux x8664、Python3.11、兼容CUDA13的NVIDIA驱动；FP32配方在H20 96GB实测显存约39GB。 终端B启动API和工作台： 打开本地工作台，或调用API： 每题返回probabilities、confidence及相应的choice、score或noul。 Score为从0开始的期望等级；Noul为yes的概率。部署脚本使用原始答案概率（calibration: unfitted）。 媒体通过服务端受信文件路径和SHA256引用： type也支持audio/video；视频用videoframes选择8或16帧。 GGUF截图采用RGB、长边≤1344；完整命令见gateway/GGUF.md。 Open weights cc-by-nc-sa-4.0 8B parameters 131,072 tokens transformers [View model](https://savrn.com/models/lite-omnijev) Model ### [male-female-chorus-separation](https://savrn.com/models/male-female-chorus-separation) [Liangjiamin](https://savrn.com/model-publishers/liangjm0121) male（男声） - female（女声） 2. 训练数据偏中文歌曲：作者用 750 首中文歌（opencpop + m4singer 数据集，700 训练 / 50 验证）训练，作者自述「缺乏一定普遍性」，归类为实验性模型。对其他语种/曲风的泛化可能下降。 3. 不是通用人声分离：它只分男女声，不分伴奏。输入应是已去伴奏的人声（vocals）。正确流程是先 Demucs / UVR / MSST 人声模型分出 vocals，再把 vocals 喂给本模型；直接丢带伴奏整首歌，效果会差。 - modelchorusbsroformerep267sdr24.1275.ckpt — 模型权重（约 503 MB，Git LFS 管理） - configchorusmalefemalebsroformer.yaml — 模型配置 - examples/ — 作者提供的示例音频（vocalsraw 原人声、vocalsmale 男声结果、vocalsfemale 女声结果） - READMESucialoriginal.md — 原作者模型卡原文 - LICENSE — CC BY-NC-SA 4.0 许可说明 - requirements.txt — 推理依赖 2. 把 modelchorusbsroformerep267sdr24.1275.ckpt 放到 MSST 的 pretrain/vocalmodels/。 3. 把 configchorusmalefemalebsroformer.yaml 放到 MSST 的 configunofficial/msstconfig/。… Open weights cc-by-nc-sa-4.0 msst [View model](https://savrn.com/models/male-female-chorus-separation) Model ### [stvg-r1-model-7b](https://savrn.com/models/stvg-r1-model-7b) [Javion](https://savrn.com/model-publishers/javion2025) This repository contains the checkpoint for STVG-R1, the first reinforcement learning framework for spatial–temporal video grounding. We finetuned Qwen2.5-VL-7B-Instruct with constructed Visual Prompt Data. If you use STVG-R1 or this checkpoint in your research, please cite Open weights cc-by-nc-sa-4.0 8.3B parameters 128,000 tokens [View model](https://savrn.com/models/stvg-r1-model-7b) Model · Robotics ### [tartanimu-xunden-iros2026](https://savrn.com/models/tartanimu-xunden-iros2026) [Xuandong Liang](https://savrn.com/model-publishers/xunden) One model, one set of weights, for the IROS 2026 TartanIMU cross-platform inertial odometry challenge. The network predicts body-frame velocity from 6-axis IMU alone for car, drone, quadruped and handheld motion; there are no per-platform experts and no model switching at inference. An all-zero submission scores exactly 1.000. The best public score is ≈ 0.20074, so this The checkpoint is self-contained: it stores the per-channel mean/std used for input standardization plus all architecture hyper-parameters, so inference needs no extra flags or training-time artefacts. --stride 5 and --tta-shifts 0,25,-25 are the inference configuration of the submitted system (see compliance item 3). Using… Open weights cc-by-nc-sa-4.0 pytorch [View model](https://savrn.com/models/tartanimu-xunden-iros2026) Model · Robotics ### [tartanimu-xunden-iros2026-rich150](https://savrn.com/models/tartanimu-xunden-iros2026-rich150) [Xuandong Liang](https://savrn.com/model-publishers/xunden) This repository is the second of the two single-model checkpoints that team Xunden selected on the Kaggle leaderboard. The first one lives at (RICH2200tv, 31-channel inputs, 200 epochs). The two checkpoints are independent single models: each generated its own selected CSV on its own, and no prediction in either CSV is an ensemble, blend or average of the two. The official per-sequence scoring service was not run on this particular CSV; its recorded result is the Kaggle public leaderboard entry above. The richer companion model in the sister repository reports the official per-sequence service numbers. The checkpoint is self-contained: it stores per-channel mean/std for input… Open weights cc-by-nc-sa-4.0 pytorch [View model](https://savrn.com/models/tartanimu-xunden-iros2026-rich150) Model · Feature extraction ### [TeraAnaly](https://savrn.com/models/teraanaly) [Tera](https://savrn.com/model-publishers/teraspace) Russian speech analysis with one frozen w2v-BERT encoder and independently callable age, gender, emotion, stress and CTC components. Decode audio once, run the encoder once, and reuse its output for any heads you need. Noncommercial use only for the TeraAnaly code and trained heads, under CC-BY-NC-SA-4.0. The original encoder weights retain their upstream CC-BY-4.0 license. See LICENSE.md. Outputs are an integer age in years, the highest gender label, the highest emotion label, and a transcript with + before stressed vowels. Emotion labels are neutral, angry, positive, sad, other; demographic labels are female, male, child (child is an age category inherited from the teacher).… Open weights cc-by-nc-sa-4.0 transformers [View model](https://savrn.com/models/teraanaly) Model · Text classification ### [vifeedback-sentiment-phobert](https://savrn.com/models/vifeedback-sentiment-phobert) [Le Thanh Dat](https://savrn.com/model-publishers/datk4) Sentiment (negative / neutral / positive) for Vietnamese student feedback about university courses. PhoBERT-base fine-tuned on UIT-VSFC with diacritic and teencode augmentation and, at every step, trained to give a real informally typed comment the label a frozen teacher gives its normalized form. Real typing changes 12% of its labels, against 18% for the same model without that training. Shipped as the ONNX FP32 graph the ViFeedback service runs, plus the PyTorch checkpoint it was exported from. Code, evaluation protocol and every number below: https://github.com/ThanhDatVN/ViFeedback-NLP-Service The model expects pyvi word-segmented, lowercase text (giảngviên nhiệttình), at most 96… Open weights cc-by-nc-sa-4.0 onnx [View model](https://savrn.com/models/vifeedback-sentiment-phobert) Model · Object detection ### [viscan-opg-weights](https://savrn.com/models/viscan-opg-weights) [Surendra goud](https://savrn.com/model-publishers/surendra08) Open weights cc-by-nc-sa-4.0 [View model](https://savrn.com/models/viscan-opg-weights) Model · Text generation ### [WikiQwen-4B](https://savrn.com/models/wikiqwen-4b) [Devon Yanitski](https://savrn.com/model-publishers/devon7y) Ask anything, get a how-to article. WikiQwen-4B is Qwen3.5-4B fine-tuned to answer every message the same way: as a tidy, step-by-step how-to article in markdown, with a picture caption above each step. Hand those captions to WikiQwen-Illustrator and they become illustrations. Send it a question ("how do I keep basil alive?"), a problem ("my bike chain keeps falling off") or just "hi", and it sends back a guide. Every reply has the same shape: - a # How to … title and a short intro - one or more ## Method N: or ## Part N: sections, or a single ## Steps - an [IMAGE: caption] line above each step, written for the Illustrator to draw - steps written as N. Bold summary. Details…, with bullets… Open weights cc-by-nc-sa-4.0 4.2B parameters 262,144 tokens transformers [View model](https://savrn.com/models/wikiqwen-4b) Model · Text generation ### [WikiQwen-9B](https://savrn.com/models/wikiqwen-9b) [Devon Yanitski](https://savrn.com/model-publishers/devon7y) Ask anything, get a how-to article. WikiQwen-9B is Qwen3.5-9B fine-tuned to answer every message the same way: as a tidy, step-by-step how-to article in markdown, with a picture caption above each step. Hand those captions to WikiQwen-Illustrator and they become illustrations. Send it a question ("how do I keep basil alive?"), a problem ("my bike chain keeps falling off") or just "hi", and it sends back a guide. Every reply has the same shape: - a # How to … title and a short intro - one or more ## Method N: or ## Part N: sections, or a single ## Steps - an [IMAGE: caption] line above each step, written for the Illustrator to draw - steps written as N. Bold summary. Details…, with bullets… Open weights cc-by-nc-sa-4.0 9B parameters 262,144 tokens transformers [View model](https://savrn.com/models/wikiqwen-9b) Model · Text to image ### [WikiQwen-Illustrator](https://savrn.com/models/wikiqwen-illustrator) [Devon Yanitski](https://savrn.com/model-publishers/devon7y) Give it a caption, get a step illustration. WikiQwen-Illustrator is a style LoRA for [FLUX.2 [klein] base 4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B). It turns a one-to-three-sentence scene description into a clean, friendly how-to illustration at 512x384. It is the picture half of WikiQwen: the chat models (4B, 9B, 35B-A3B) write an [IMAGE: caption] line above every step, and this LoRA draws it. Inside a WikiQwen article, a step looks like this. The first line is the Illustrator's prompt, and the second is the step it illustrates: - No trigger word. The training captions describe content only, with no style words, so the style comes along automatically. It takes a… Open weights cc-by-nc-sa-4.0 diffusers [View model](https://savrn.com/models/wikiqwen-illustrator) ## Questions ### Can I use Creative Commons Attribution-NonCommercial-ShareAlike 4.0 models commercially? Not without separate permission. CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission. ### Which Creative Commons Attribution-NonCommercial-ShareAlike 4.0 models are most downloaded? By monthly downloads reported by the Hugging Face Hub: finbert (3.9M); wav2vec2-large-robust-24-ft-age-gender (2.2M); inclusively-reformulation-it5 (2.2M). ## Other Licenses - [apache-2.0](https://savrn.com/models/licenses/apache-2-0) 3436 - [mit](https://savrn.com/models/licenses/mit) 1346 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 216 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 172 - [bsd-3-clause](https://savrn.com/models/licenses/bsd-3-clause) 108 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 41 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 33 - [unknown](https://savrn.com/models/licenses/unknown) 33 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 29 - [gpl-3.0](https://savrn.com/models/licenses/gpl-3-0) 21 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 [See all](https://savrn.com/models/licenses)