Search public pages, research tools, and SAVRN solutions.
SAVRN Model Hub
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
Updated 2026-09-18 · How the library is built
2,760 models, sorted by most downloaded.
Roof detection model for remote sensing imagery, fine-tuned using RT-DETR. The following example shows roof detections produced by the model: Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
https://huggingface.co/typeform/distilbert-base-uncased-mnli with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
Model · Video classification
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - trainingsteps: 348 - Transformers 4.49.0 - Pytorch 2.6.0+cu126 - Datasets 3.3.2 - Tokenizers 0.21.0
A high-performance YOLO11n instance segmentation model fine-tuned for detecting and segmenting speech bubbles in manga/comic images. Left: Segmentation Loss (Train vs Val) | Right: Mask mAP Metrics over epochs This model was trained on a combined dataset of: 1. MS92/MangaSegmentation - Manga panel and bubble segmentation dataset 2. Manga109 - Large-scale manga dataset with speech bubble annotations If you use this model in your research, please cite: This model is released under the Apache 2.0 License. - Ultralytics for the YOLO framework - MS92/MangaSegmentation dataset - Manga109 dataset
Embedding model for octomind capability / skill auto-activation: ibm-granite/granite-embedding-30m-english (30M params, 6 layers, 384-dim, CLS-pooled, prefix-free, English) fine-tuned on trigger phrases from the octomind-tap capabilities + skills catalog and blended back into the base as a WiSE-FT model soup, which beats both the base and the raw fine-tune on the runtime gate (mean-of-top-3 cosine + threshold + margin). CachedMultipleNegativesRankingLoss (scale 10) on in-class pairs and positive-aware hard-negative triplets, MatryoshkaLoss over [384, 256, 192, 128, 96], then weight interpolation with the base. - model.safetensors + 1Pooling/ — sentence-transformers layout (fp32).…
This model was produced by fine-tuning the OpenVLA 7B model via LoRA (r=32) on the LIBERO-10 (LIBERO-Long) dataset from the LIBERO simulation benchmark. We made a few modifications to the training dataset to improve final performance (see the OpenVLA paper for details). Below are the hyperparameters we used for all LIBERO experiments: - No gradient accumulation (i.e. gradaccumulationsteps == 1) - shufflebuffersize == 100000 See the OpenVLA GitHub README for instructions on how to run and evaluate this model in the LIBERO simulator.
X-CLIP model (large-sized, patch resolution of 14) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. This model was trained using 16 frames per video, at a resolution of 336x336. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs. This allows the model to be used for tasks like zero-shot, few-shot or fully…
MobileBERT is a thin version of BERTLARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. This model was fine-tuned from the HuggingFace checkpoint google/mobilebert-uncased on SQuAD1.1. CPU: Intel(R) Core(TM) i7-6800K CPU @ 3.40GHz Memory: 32 GiB GPUs: 2 GeForce GTX 1070, each with 8GiB memory GPU driver: 418.87.01, CUDA: 10.1 It took about 3 hours to finish. Note that the above results didn't involve any hyperparameter search.
Topology-Aware Knowledge Distillation from Qwen3-30B-A3B → 1.7B TopologicalQwen is a 1.7B parameter model distilled from Qwen3-30B-A3B using Topological Knowledge Distillation (TKD) — a methodology that treats the teacher's output distribution over a concatenated token stream as a bounded variation (BV) function and decomposes knowledge transfer into three channels via the Mesh Fundamental Identity: 1. Smooth distillation (AC component) — Standard KL divergence over regions where the teacher's distribution varies continuously. This is what every other KD method does and stops at. 2. Jump corrections (D^j f) — Explicit correction terms at conceptual boundaries where the teacher's…
With Blackhole Rope Dynamics This model builds on the original 421M TAMELM-AFMoER by introducing the Blackhole Rope (BHR) mechanism—a dynamic field-based routing system designed to stabilize, amplify, and concentrate information flow across multiple temporal scales. While the original AFMoER established efficiency in routing-based intelligence, the BHR variant explores how structured gravitational-like attractors can further enhance reasoning depth without exponential increases in computation or parameters. The Blackhole Rope is a symplectic, multiscale vortex mechanism inside AFMoER that: If AFMoER routes are like neuronal pathways, the Blackhole Rope is the myelinated tether that keeps…
Paper: SciFive: a text-to-text transformer model for biomedical literature Authors: Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet For more details, do check out our Github repo.
Purpose: Full-scale cognitive reasoning model with self-organizing memory and generative symbolic evolution SymbioticLM-14B is a 17.8-billion-parameter symbolic–transformer hybrid that couples high-capacity neural representation with structured symbolic cognition. It supports persistent memory, entropic recall, multi-stage symbolic routing, and self-organizing knowledge structures. This is an experimental research checkpoint — the capability claims below describe architectural intent, not benchmarked results (see Limitations). This model is ideal for advanced reasoning agents, research assistants, and symbolic math/code generation systems. - Long-form symbolic theorem generation and proof…
This is the model for abstractive summarization for Russian based on rut5-base. Source maxlength: 600 Target maxlength: 200 norepeatngramsize: 4 numbeams: 5 Source maxlength: 600 Target maxlength: 200 norepeatngramsize: 4 numbeams: 5
Purpose: Long-memory symbolic reasoning + high-fidelity language generation SymbioticLM-8B is a state-of-the-art hybrid transformer model with built-in symbolic cognition. It combines an 8B Qwen-based transformer with modular symbolic processors and a persistent memory buffer. The model supports both general conversation and deep symbolic tasks such as theorem generation, logical chaining, and structured reasoning with retained memory across turns. - General symbolic reasoning and logical conversation - Code + math proof modeling - Not instruction-tuned (e.g., chat-style inputs may require prompt engineering) - Larger memory buffer may increase CPU load slightly - Symbolic inference is…
SymbioticLM is a hybrid symbolic–neural language model that integrates a frozen transformer backbone (Qwen2ForCausalLM) with a suite of symbolic cognitive modules for adaptive, interpretable reasoning. The architecture fuses neural token-level generation with symbolic introspection and reasoning: - Dynamic Thought Evolution with Helical Encoding and DNA-Inspired Memory (DTE-HDM) Enables structured long-term memory and spiral-context encoding across tokens. - Multi-Agent Symbiotic Response Mechanisms (M.A.S.R.M) Coordinates symbolic-neural agents via gated attention and adaptive response layers. - QwenExoCortex Projects contextual hidden states from the Qwen model into a symbolic fusion…
The first defense AI reasoning model on Hugging Face. Shepherd-Alpha is a tactical reasoning model fine-tuned on dual-perspective military scenario analysis using BiCell Depth Dispersal — a novel training methodology that partitions transformer layers by abstraction depth and trains them asymmetrically to separate representation encoding from task-specific reasoning. Developed by Convergent Intelligence LLC: Research Division Given a tactical scenario, Shepherd-Alpha produces structured dual-perspective analysis: - Attack reasoning — how an adversary would exploit the situation - Defense reasoning — how to counter, mitigate, and survive The model is trained to think like both attacker and…
Purpose: Lightweight, memory-augmented reasoning model for CPU and embedded inference SymbioticLM-1B is the compact version of the SymbioticAI architecture. It fuses Qwen’s rotary transformer design with a symbolic processing pipeline and a persistent episodic memory. Though smaller in parameter count, it retains the full cognitive engine: symbolic memory, dynamic thought evolution, and entropy-gated control. This model is ideal for symbolic reasoning in constrained environments — like research agents, lightweight assistants, and memory-efficient logical processing. - Procedural planning, math modeling, small-code generation - Less fluent in free-form language than larger variants…
SmolLM2Prover is a specialized, fine-tuned version of prithivMLmods/SmolLM2-CoT-360M. While retaining the strong conversational abilities of its base model, this version has been specifically enhanced to excel at deep thinking, logical reasoning, and higher-level mathematics, with a focus on generating step-by-step proofs and explanations (Chain-of-Thought). The model was fine-tuned using multiple rounds of Supervised Fine-Tuning (SFT) with the TRL library on a curated dataset, enhancing its ability to follow complex instructions and reason through problems. This model is intended to be used for text generation tasks that require logical reasoning or advanced conversation. The easiest way…
This model is a fine-tuned version of t5-small on the cnndailymail dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5.6e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 8 - Transformers 4.14.0 - Pytorch 1.5.0 - Datasets 2.3.2 - Tokenizers 0.10.3
SAGI (Swarm AGI) is a novel causal language model that integrates swarm intelligence dynamics with transformer architecture. The model treats cognition as a dynamic, adaptive system where multiple internal "agents" collaborate through differentiable routing, trust mechanisms, and shared memory. V3.2 introduces a revolutionary Self-Assessment Layer, allowing the system to predict its own performance, identify skill gaps, and autonomously design its own learning curriculum. 1. Pre-Assessment: Predict success, identify risks, recommend strategy. 2. Execution: Generate with selected strategy. 3. Real-Time Monitoring: Catch and correct errors during generation. 4. Post-Assessment: Update skill…
Core AI is Apple's on-device ML runtime in iOS 27 / macOS 27 and the successor to Core ML: PyTorch models are exported with Apple's coreai-torch (LLMs: coreai.llm.export) into.aimodel bundles that run on the GPU or the Neural Engine, e.g. Qwen3-8B 4-bit decodes at 94 tok/s on an M4 Max GPU, MLX 90 under the same protocol (apple-silicon-llm-bench, macOS 27 beta 26A5353q, 2026-06-11). This model has no row on DeviceMark, the on-device LLM leaderboard. V-JEPA 2 (Meta AI) running natively on the Apple Core AI engine — the zoo's first world model: a self-supervised video encoder that learns by predicting in representation space (JEPA), here with the Something-Something v2 action head (174…
This repository contains a checkpoint of the Pi0 model (HF implementation | Paper) finetuned on the BridgeV2 dataset for robotic manipulation tasks. The model is later used for testing on the Simpler Environment and our INTACT Probing Suite for the generalization boundaries of VLA models. Paper: From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models Or directly in python with Lerobot, see blow: First, install lerobot Then For more details please refer to our paper and code Checkpoint choice After training 15 epochs, we sweep the checkpoint at epoch 1, 2, 3, 4, 5, 10, 15 for performance on the original 4 Bridge tasks in the SimplerEnv, and choose…
SAGI is a novel causal language model that integrates swarm intelligence dynamics with transformer architecture. The model treats cognition as a dynamic, adaptive system where multiple internal "agents" collaborate through differentiable routing, trust mechanisms, and shared memory. - Episodic + Semantic Memory: Dual memory system with trainable retrieval utility The swarm processes observations derived from token embeddings, updating its internal state S. This state conditions the transformer's attention patterns and feed-forward activations via learned projections, creating bidirectional information flow between symbolic (tokens) and subsymbolic (swarm dynamics) processing. - Educational…
A 2B-parameter Qwen3.5 fine-tune, part of the Opus-Distil line in the reaperdoesntknow open-weight portfolio. Text-generation / reasoning model, trained with Unsloth + Hugging Face TRL.
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Recognition and synthesis models, grouped so the two directions are easy to compare.
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.
