Open-Weight Models Under Apache License 2.0

Model

vector-bbp-v1

0ai

Authorized bug bounty (BBP), vulnerability disclosure (VDP), and contracted pentest copilot. - Fine-tuned only on local RTX 5070 (glasseye) — no cloud GPUs - Continued from GlassEye BBP v1 with VECTOR Analyst system prompt + auth hardening (no invented program IDs) Scope parsing, in-scope methodology, CVSS/CWE report drafting, coordinated disclosure coaching. Unauthorized testing, ransomware, phishing kits, credential theft, production data dumps.

Model

vector-bbp-v1-gguf

0ai

Authorized BBP/VDP/pentest only. Never invent program IDs.

Model

vedic-qwen2.5-14b-GGUF

GnanaSreekar

A fine-tuned model of Qwen/Qwen2.5-14B-Instruct specialized in classical Vedic Astrology (Jyotish), trained on over 8,700 synthesized question-answer pairs and chart application examples derived from classical Sanskrit texts: Brihat Parashara Hora Sastra (BPHS) Mantreswara's Phaladeepika Bhrigu Nandi Nadi Classical varga, avastha, shadbala, and dasha frameworks. Run directly on your local machine using Ollama: Or download the.gguf file directly and use with llama.cpp

Model · Text classification

vega-08b-public-intents

Nandakishor M

Inference on a single T4, end to end, in the browser. 800 million or 4 billion parameters. A 73,728-token context. Images. Running on your own hardware. That combination is the point: a decision model small enough to sit inside your own process, that can read a whole contract in one pass and look at a picture, and that still beats a hosted reference model on the tasks below. A new architecture with its own training and calibration method. The language model inside it is frozen and never trained; everything learned lives in a small physics engine on top of it. Both are in this repository and take the same code path. The 0.8B sits at the root because that is where it has always been; the 4B…

Community abliteration and quantization of tsinghua-sigs-robot-lab/VeriLoop-E2, fixed revision 9379d199adcc44acdf836558037163878e3a37ae. This is not an official Tsinghua release. Model architecture is Qwen35ForConditionalGeneration; the upstream names the base Qwen3.8-27B. Q4KM main model and separate F16 vision projector. No importance matrix was used. Full-precision conversion intermediates are excluded from this release. A bounded six-candidate Heretic 1.4.0 search selected per-layer strength 1.2; 96 of 128 targeted residual-output matrices changed and 32 zero updates remained unchanged. The small selection set improved from 16/16 to 4/16 refusal markers, missing its original ≤1…

Community abliteration and quantization of tsinghua-sigs-robot-lab/VeriLoop-E2, fixed revision 9379d199adcc44acdf836558037163878e3a37ae. This is not an official Tsinghua release. Model architecture is Qwen35ForConditionalGeneration; the upstream names the base Qwen3.8-27B. AutoRound W4A16, symmetric group 128, 256 public Pile calibration samples, 512 tokens, 200 iterations, batch 4. Eligible weights are INT4; small hybrid projections, activations and retained weights are BF16. All source tensors are represented; the 333 vision tensors are preserved exactly. A bounded six-candidate Heretic 1.4.0 search selected per-layer strength 1.2; 96 of 128 targeted residual-output matrices changed and…

Model · Text generation

Vertex-Core-Gemma

Denis Sanchez Leyva

Vertex Core is a specialized AI software-engineering model developed by Vertex Coders LLC. It is based on Google's Gemma 2 9B IT and fine-tuned using LoRA/QLoRA techniques to improve its behavior for software-engineering workflows, code generation, code modification, debugging, security-oriented code analysis, and tool-oriented development tasks. Vertex Core is designed to serve as the coding and reasoning core of agentic software-engineering systems. Vertex Core is under active development. Vertex Core is intended for applications involving: The model is particularly intended to operate as part of an agentic system where the surrounding application provides access to repositories, files…

static quants of https://huggingface.co/simpledirect/Vinci-Cyber-30B-1.0 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…

weighted/imatrix quants of https://huggingface.co/simpledirect/Vinci-MLE-8B-1.0 For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Vinci-MLE-8B-1.0-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: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

Model · Image and text to text

ViSkill-FrozenLake

Hongxing Li

This repository contains ViSkill-FrozenLake and its visual skill library, introduced in ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills. ViSkill-FrozenLake is a visual agent model for FrozenLake, built upon Qwen2.5-VL-3B-Instruct. It represents successful interactions as reusable visual skill cards. Geometry-aware retrieval guides the agent, while PPO with skill-guided rewards and online skill distillation jointly improve the policy and skill library. Model files are stored at the repository root, with the accompanying visual skill library in skilllibrary/. For the full ViSkill agent pipeline, including skill retrieval and environment interaction, please refer to our code…

This PEFT adapter was trained on a 120,000-row stratified subset, not the entire training split, of Visual Jev decisions v1 at revision 687c745c34846d104ee85af802b9fd444a854f5d. It answers a task-specific question about an image with a normalized box, choice, or short text. The two published prediction logs contain the same 1,000 held-out test IDs. The 120k adapter improved all five selected-subset scores, including mean grounding IoU from 0.530 to 0.598, box choice accuracy from 94.0% to 97.5%, and spatial decision accuracy from 90.0% to 94.5%. This is not a full test-split benchmark. Modal's billing report measured $8.23 metered for the 120k staging, training, benchmark, and automatic…

This PEFT adapter was trained on a 40,000-row stratified subset, not the entire training split, of Visual Jev decisions v1 at revision 687c745c34846d104ee85af802b9fd444a854f5d. It answers a task-specific question about an image with a normalized box, choice, or short text. The GitHub composite shows selected held-out predictions with annotated photos. Its companion JSON retains full predictions. Published train and evaluation questions largely use five fixed templates. COCO instance annotations supply grounding, box choice, and left/right questions; Visual Genome v1.2 supplies selected color and relation labels. Objects, boxes, and targets vary by photo, and a photo yields only supported…

English | 中文 Community-maintained fork of Nunchaku. Nunchaku is an SVDQuant inference engine for 4-bit diffusion models (paper: SVDQuant). The upstream project has not been actively maintained for a long time. This fork keeps the original capabilities while extending model and quantization support, and distributes prebuilt wheels on Hugging Face. Quantized inference for three additional models. Published wheels cover Linux x8664, Linux aarch64, and Windows, all built for CUDA 13.0: - Linux x8664: Python 3.11 + PyTorch 2.11; Python 3.11 / 3.12 / 3.13 + PyTorch 2.14 File names are listed under Prebuilt Wheels. Anima checkpoints store plain INT8. frompretrained(..., device="cuda") packs them…

Model · Text generation

Viu-1.5B-MoE

Vipin Kumar

Viu-1.5B-MoE is a sovereign Indian Large Language Model featuring a 48-Layer Ultra-Deep Frontier Mixture of Experts (MoE) architecture designed for deep hierarchical reasoning, Indic multilingual fluency (Hindi, Hinglish, English), and high-speed on-device inference. 1. 48-Layer Ultra-Deep Reasoning: Deep hierarchical abstraction across 4 cognitive tiers (12 layers each: Token Mechanics $\rightarrow$ Multilingual Alignment $\rightarrow$ Domain Knowledge $\rightarrow$ Deep Deductive Logic). 2. Compressed Sparse Attention 2 (CSA2): DeepSeek-V4.1 style low-rank KV compression saving 80% KV-cache memory for long-context inference on consumer GPUs. 3. Manifold-Constrained Hyper-Connections…

Model · Text generation

ViuMini-MoE-242M

Vipin Kumar

Viu-1.5B-MoE is a sovereign Indian Large Language Model featuring a 48-Layer Ultra-Deep Frontier Mixture of Experts (MoE) architecture designed for deep hierarchical reasoning, Indic multilingual fluency (Hindi, Hinglish, English), and high-speed on-device inference. 1. 48-Layer Ultra-Deep Reasoning: Deep hierarchical abstraction across 4 cognitive tiers (12 layers each: Token Mechanics $\rightarrow$ Multilingual Alignment $\rightarrow$ Domain Knowledge $\rightarrow$ Deep Deductive Logic). 2. Compressed Sparse Attention 2 (CSA2): DeepSeek-V4.1 style low-rank KV compression saving 80% KV-cache memory for long-context inference on consumer GPUs. 3. Manifold-Constrained Hyper-Connections…

VIYA reads Vietnamese text and returns typed decisions with calibrated confidence in a single forward pass. It does not generate text: you describe the question and the options in plain language, and VIYA scores every option. Options are free text, so you can add or rename them without retraining. - Vietnamese fact-checking. 87.6 macro-F1 on ViFactCheck with gold evidence (human: 84.9). When it has to find the evidence itself in the full article, it scores 78.7, ahead of Gemini 1.5 Flash, XLM-R large and Mistral 7B. - Full fact-checking pipeline. On ViWikiFC, VIYA finds the right evidence sentence and reaches the right verdict 75.7% of the time; the best published pipeline reaches 67.0%.…

static quants of https://huggingface.co/NandiAi/VKP-Omni-2B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And…

Model · Visual question answering

vlm-calibration-prefix-vqav2

Bhaskar C

A small non-autoregressive yes/no visual question answering model built for research on calibrated decisions. It answers a yes/no question about an image in one forward pass, with no generation and no verbalised confidence. The confidence is the softmax over two token logits followed by a single post-hoc temperature. - Image. A frozen SigLIP2-base encodes the image into its pooled vector (pooleroutput, 768-d). - Prefix token. That vector becomes one prefix token, prepended to the input embeddings of ModernBERT-base: - anchor is a learned token, initialised from the " image" embedding. - alpha is a scalar gate, initialised to 0, so the model starts as exactly the text-only model. - gmax caps…

Model · Text generation

vnpen-writer-2b-v0.1-preview

VNPen LLM Project

VNPen is MewBaka Studio's visual-novel model series. The writer edition is for script writing, de-AI rewriting, and generating example scenes from a mood brief. Output format is one script line per line: speaker：text, with narration written as 旁白：. The base Qwen/Qwen3.5-2B is multimodal. Its checkpoint carries 297 model.visual. tensors (a depth-24 / hidden-1024 / patch-16 ViT) and 15 mtp. tensors for multi-token prediction. This project is text-only. In transformers, AutoModelForCausalLM on a qwen35 config builds Qwen35ForCausalLM over a Qwen35TextConfig — so the vision weights were never loaded at any point: not for training, not for merging, not for saving. Verified on the published…

checkpoints/finalcheckpoint: LoRA adapter and tokenizer files.

The Von System One decision model (ModernBERT-large, 395M, English, 8192-token context), exported to ONNX fp32 and packaged for Verdict -- a high-performance serving engine for System One decision models. Serve it with one command: Pick the image that matches the host. The -v mounts cache the model, so only the first run downloads it. Add -e VERDICTUSEMODELSCOPE=1 and use sgyaqing/von to fetch from ModelScope instead of the hub; add -e HFENDPOINT=https://hf-mirror.com if the hub is slow or unreachable. Endpoints: the standard decision protocols POST /v1/systemone and POST /v1/decisions, native POST /v1/choice | /v1/score | /v1/noul, plus an OpenAI-compatible layer (/v1/chat/completions…

Model · Text to speech

VoxCPM2

K1ng Tai

VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data. - 30-Language Multilingual — No language tag needed; input text in any supported language directly - Voice Design — Generate a novel voice from a natural-language description alone (gender, age, tone, emotion, pace…); no reference audio required - Controllable Cloning — Clone any voice from a short clip, with optional style guidance to steer emotion, pace, and expression while preserving timbre - Ultimate Cloning — Provide reference audio + its transcript for audio-continuation cloning; every vocal nuance…

An INT8-quantized repack of openbmb/VoxCPM2, prepared so the model can be loaded and run entirely inside a web browser by shi3z/voxcpm2web (a WASM + WebGPU port of Nothing about the model architecture was changed. This repository exists to solve 1. wasm32 has a 4 GB address space. The upstream checkpoint is 4.27 GiB of weights plus a 359 MB audiovae.pth. 2. Quantizing during load costs VRAM you may not have. Doing it ahead of time means the browser never materializes the full-precision tensors at all. There is no separate audiovae file: the AudioVAE weights are already merged in, so a browser needs exactly one large download instead of two. Both rows produce applied=632 missing=0 unused=0…

Model · Speech recognition

Voxtral-Mini-3B-2507-gguf

MyFlow by Growlioo

GGUF conversions of mistralai/Voxtral-Mini-3B-2507 for use with transcribe.cpp. Ported from upstream commit pinned 2026-06-06. Validated against the Transformers reference at transcribe.cpp commit Offline audio-LLM speech-to-text and speech translation. A Whisper-large-v3 bidirectional audio encoder feeds a 4-frame-group projector (375 audio tokens per 30 s chunk) into a Ministral-3B causal LM (30 layers, GQA 32/8, NEOX RoPE, SwiGLU) via audio-token injection. Takes a 16 kHz mono WAV and produces a transcript via greedy decoding; speech translation runs through the mistral-common instruct template. The smaller sibling of Voxtral Small 24B — same encoder, projector, log-mel frontend, and…

Model · Feature extraction

voxtral-mini-audio-extractor

Vxltxr Llc

A lightweight standalone audio feature extractor derived from Voxtral-Mini-3B-2507. This repository isolates the Whisper-based audio encoder and multi-modal projector from the original 3B language model. The extracted module is intended for offline audio preprocessing, dataset preparation, feature caching, and downstream multimodal training pipelines. The language-model decoder is not included. It does not contain the 3B LLaMA language-model decoder. For offline preprocessing, loading the complete multimodal language model is unnecessary when the only required output is the projected audio representation. This standalone checkpoint can therefore be used as a dedicated audio feature…

Preview checkpoint, not yet evaluated. Final student of a 200-step DMD run (E0029 Variant V0403). It differs from memset0/vsqa-preview-14b (V0362) in two ways: - critic (fake score) learning rate 2e-6 instead of 4e-7 (critic update ratio 1 unchanged); - the linear layers' NVFP4 QAT uses global scales fixed to 1.0 (nvfp4qattraings1) for activations and weights, instead of the dynamic 448·6/max|x| recomputed every forward. All at 77 frames, 1280×768, global batch 16, from the original Wan2.1-T2V-14B weights: 1. Dense NVFP4 per-layer reconstruction, 250 steps. 2. Plain ODE initialization (endpoint regression), 500 steps, VSA C256 cube (4,8,8), sparsity 0.9, NVFP4 attention + linear QAT. 3. DMD…

Model · Audio classification

wakehubert-wakewords

OpenVoiceOS

Ready wake-word models for OpenVoiceOS, trained with wakeforge. Each model is a small GRU classifier that reads features from WakeHuBERT tiny, a 0.64M-parameter speech feature extractor distilled from HuBERT-base. A model scores the last 1.5 s of audio (75 feature frames) and outputs a logit; its sigmoid is the probability that the window holds the wake word. Try them in your browser: WakeHuBERT wake-words Space runs every model here on your microphone or an uploaded file, with a live score and the calibrated threshold. Everything runs locally in the browser. The repository holds one ONNX file per word under models/, and models.json, which lists each model's word, featurizer, calibration…

Исторический идентификатор ветви и файлов — Vol2. WAL2 использует новую исходную Qwen3.8-FP8; старый WAL RC1 на Qwen3.6 со sparse/WALB2 не является parent этих весов. Основной свежий артефакт этого снимка — E022-Fixed128, потомок E020-B1024. Завершённая диагностика: 69/136 (50,74%), лучше родителя 64/136 по сумме, но AIME25 0/30 против 2/30. E020-B1024 сохранён отдельно как контрольный кандидат. Утверждения о превосходстве E022 по всем задачам нет. Полный GSM8K 84,69% относится только к E017. Слабое AIME25 и регрессии более новых вариантов сохранены в отчёте. Артефакт текстовый. Визуальная часть исходной conditional-generation модели не преобразовывалась, не обучалась и не выпускается.…

Model · Text to video

Wan2.1-T2V-14B

AmateurGuy23

In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B…

We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository also includes our I2V-A14B model, designed for image-to-video generation, supporting both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it achieves more stable video synthesis with reduced unrealistic camera movements and offers enhanced support for diverse stylized scenes. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2 Text-to-Video - [x]…

Model · Robotics

Wan2.2-5B-PI-SIMPLE

Star Vision Language Action Models

This model is a StarVLA StarVLA-WM-Wan-PI (WanPI) policy jointly trained on 12 SIMPLE Unitree G1 humanoid tasks. It uses one shared checkpoint across all tasks; there is no task-specific fine-tuning or task-specific checkpoint selection. The training job was configured through 120,000 steps. Results in this card refer specifically to the 100,000-step checkpoint, not finalmodel or the 120,000-step checkpoint. The image is encoded by the Wan VAE and the instruction by UMT5. Hidden features from all 30 Wan transformer blocks are projected to 1,024 dimensions and paired layer by layer with the Action DiT. Even-indexed Action-DiT blocks cross-attend to the matching Wan features; odd-indexed…

This qwen35 model was trained 2x faster with Unsloth and Huggingface's TRL library.

The base model pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli Abstract We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech…

Model

wav2vec2-xls-r-300m

losCrossos

Facebook's Wav2Vec2 XLS-R counting 300 million parameters. XLS-R is Facebook AI's large-scale multilingual pretrained model for speech (the "XLM-R for Speech"). It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages. When using the model make sure that your speech input is sampled at 16kHz. Note: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out this blog for more information about ASR. Authors: Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh…

Model · Zero-shot classification

wazn-2b-v0.1

Numidlabs

returns a probability distribution over a set of labels you supply, each with an optional definition and few-shot examples. Nothing is generated. Experimental. For trying the model out, not for production. TODO: known weak spots, training data summary, evaluation results. The head weights are released under Apache-2.0. The backbone keeps its own license; see Qwen/Qwen3.5-2B-Base.

Model · Robotics

WB-WAM-HumanoidArena

WB-WAM

This repository contains seven HumanoidArena post-train checkpoints under humanoidarenanative50/: boxshelf, hammer, kickfootball, obstaclenavigation, opendoor, punchmarkers, and sitsofa. Each task directory has a checkpoint, its resolved training config.yaml, and datasetstats.json. Post-training uses official SONIC reference actions at their native 50 Hz rate, with separate normalization statistics for each task. Download the HumanoidArena checkpoints into a local directory: Training and evaluation instructions are in the WB-WAM repository. These results were obtained with Isaac Sim 5.1.0 on an NVIDIA RTX 5090 GPU, using three seeds and 20 episodes per seed for each task. Values are the…

Model · Robotics

WB-WAM-Pretrain-Midtrain

WB-WAM

This repository contains the full pre-train checkpoint and the PICO mid-train checkpoint. The mid-train model was initialized directly from the pre-train model. Each checkpoint has its resolved training config.yaml and datasetstats.json. Training code and instructions are in the WB-WAM repository.

Model

weather-rescue-brazil-reader

Gabriel Bueno

A small open model that reads one printed table row out of a scanned nineteenth-century meteorological table and returns its cells as text. It is not a chatbot, not a general OCR model, and not a climate model. It reads a strip of paper and writes back numbers. Trained and evaluated entirely on Brazilian historical records, but the interesting result is that it reads layouts it has never seen — and usually with no labelled rows at all. Of the 18 layouts this project describes, two ever needed hand-labelling; the other fifteen were added by writing a JSON description of the columns and running the pipeline. docs/ADDING-A-PUBLICATION.md is the path and the evidence. Base: Qwen/Qwen3.5-2B…

Model · Object detection

web-sdk-pp-rotated-detection

Chen Mohan

由chenmohan维护，非Paddle官方账号。PP-YOLOE-R-s 1024 FP32，DOTA15类单帧遥感旋转框检测，33,161,415字节。 Apache-2.0采用依据为固定官方项目声明与模型表，未发现独立权重许可文本；完整来源、转换和边界见模型卡及LICENSE/NOTICE。 Maintained by chenmohan, not the official Paddle account. Single-image DOTA15 rotated detection, PP-YOLOE-R-s 1024 FP32. Apache-2.0 is adopted from the pinned project license and model table; no separate weight-specific license text was found. See the cards for provenance, conversion and desktop verification scope.

A allenai/Olmo-3-7B-Instruct policy trained as a multi-turn search agent (Search-R1 style) with Process-GRPO: a process reward model (Olmo-3-7B-Think verifier) scores each turn, with per-(group, turn-position) advantage normalization and verifier prompts that include the retrieved tool responses and the gold answer. The model at the repository root is the final policy (training step 360). Intermediate checkpoints are provided under step / subfolders. - step20/ — intermediate checkpoint at training step 20 - step40/ — intermediate checkpoint at training step 40 - step60/ — intermediate checkpoint at training step 60 - step80/ — intermediate checkpoint at training step 80 - step100/…