π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and…
SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
2,760Models
859Datasets
254Papers
1,692Publishers
5,040Sourced relationships
Updated 2026-09-18 · How the library is built
2,760 models, sorted by most downloaded.
A 69M parameter causal language model built on the Mixture-of-Attentions (MoA) architecture — distance-based metric attention that respects the triangle inequality by construction, not approximation. Every attention head operates in a proper metric space. The geometry is enforced, not hoped for. Standard transformers compute attention as a dot product: Q·Kᵀ. This has no geometric meaning — it's a bilinear form, not a distance. Two tokens can be "close" by dot product while violating basic metric properties. MoA replaces this with negative squared distance under a learned diagonal Mahalanobis metric, then enforces the triangle inequality through a regularizer over random triples sampled…
weighted/imatrix quants of https://huggingface.co/DeepCybo/PhysBrain1.5-8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/PhysBrain1.5-8B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. 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…
Paper: Zheng et al., 2025, “X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model” (arXiv:2510.10274) Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich robotic data sources, X-VLA introduces a Soft Prompt approach with minimally added parameters: we infuse prompt-learning concepts into cross-embodiment robot learning, introducing separate sets of learnable embeddings for each distinct embodiment. These embodiment-specific prompts empower VLA models to exploit cross-embodiment…
This is the model card of a transformers model that has been pushed on the Hub. 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. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces. DISC treats training…
Using llama.cpp release b10068 for quantization. All quants made using imatrix option with dataset from here Run them in your choice of tools: Note: if it's a newly supported model, you may need to wait for an update from the developers. Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings and output weights quantized to Q80 instead of what they would normally default to. First, make sure you have huggingface-cli installed: Then, you can target the specific file you want: If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: You can either specify a new local-dir…
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. This is V-JEPA 2 model with video classification head pretrained on Something-Something-V2 dataset. To run V-JEPA 2 model, ensure you have installed the latest transformers
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. To run V-JEPA 2 model, ensure you have installed the latest transformers: V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs. To load a video, sample the number of frames according to the model. For this model, we use 64. To load an image, simply copy the image to the desired number of frames. For more code examples, please refer to the V-JEPA 2…
This is the model card of a transformers model that has been pushed on the Hub. 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. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces. DISC treats training…
Model · Image and text to text
swiftvln-satnav-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed
SwiftVLN: training and evaluation code for these checkpoints. - SatNav: satellite-image navigation environments, datasets, and evaluation tools. This checkpoint is designed for SwiftVLN on SatNav, the continuous-state vision-and-language navigation benchmark over satellite imagery. It predicts short navigation-action sequences from an instruction, the current RGB window, and sampled visual memory. - swiftvln-satnav: SwiftVLN trained and evaluated on SatNav - 3b: Qwen2.5-VL 3B backbone - 1ep: trained for one epoch - f32s4: uses a 32-frame window and predicts four actions - overlap0: uses non-overlapping training windows - pf-h8: uses per-frame memory with up to eight history frames…
Part of the DistilQwen3 Series by Convergent Intelligence LLC: Research Division This is a GGUF-quantized variant. The mathematical foundations (Discrepancy Calculus, Topological Knowledge Distillation) are documented in the source model's card. The discrepancy operator $Df(x)$ and BV decomposition that inform the training pipeline are preserved through quantization — the structural boundaries detected by DISC during training are baked into the weights, not dependent on precision. DistilQwen Collection — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The…
[[Paper]](https://arxiv.org/pdf/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM) GraspMolmo is a generalizable open-vocabulary task-oriented grasping (TOG) model for robotic manipulation. Given an image and a task to complete (e.g. "Pour me some tea"), GraspMolmo will point to the most appropriate grasp location, which can then be matched to the closest stable grasp. Running the above code could result in the following output: To predict a grasp point and match it to one of the candidate grasps, refer to the GraspMolmo class. First, install graspmolmo with and then…
An English LFM2.5 2.6B checkpoint associated with the Trendyol Cybersecurity Instruction Tuning Dataset. This repository contains both Transformers-format model files and local GGUF exports. This is a research release. The repository does not currently publish benchmark, baseline-comparison, or safety-evaluation results. Transformers assets include model.safetensors, configuration files, tokenizer files, and a chat template. Keeping both formats in one repository is convenient, but users should explicitly choose the path that matches their runtime. The checked configuration includes a bitsandbytes quantization block. Pin and test the exact Transformers, Accelerate, bitsandbytes, and device…
MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the bimanual YAM mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and bimanual YAM policy inference. Use this checkpoint for bimanual YAM inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="yamdualmolmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete…
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. The enhancements were integrated with the existing AGI system through: 1. Compatibility Layer: Ensuring new components work with existing AGI Core 2. Unified State Representation: Combining enhanced capabilities with existing state 3. Enhanced Continuous Learning: Upgrading the learning system with new capabilities 4. Performance Monitoring: Tracking improvements through validation systems - Successfully…
Model · Text generation
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-q4v3-groot16
An OpenRLHF GRPO reinforcement-learning checkpoint for Qwen3-4B. - Saved at global step 16 of RL run seededrlbaseramp25stoppengen4kep2ncp10q4v3groot16. - This is the best checkpoint by pass@8 so far in this run (evaldefaultpass8 = 0.1244). Trained and validated on the cobalt-train ≤2/64 frontier (canonical cleaneval prompts): 1833 train / 112 held-out val problems the base model solved on at most 2 of 64 samples under the iidcanonical@64 hardness scan. Val evals sample at temperature 1.0 (matching the cleaneval frontier eval). Reward signal: binary code-correctness (1.0 if the generated program passes the problem's tests, otherwise 0.0). Eval metrics at this checkpoint (held-out val, 8…
이 모델은 kobart모델을 문서요약, 도서자료요약, 요약문 및 레포트 생성 데이터로 fine-tuning한 모델입니다.
static quants of https://huggingface.co/Locutusque/OpenCerebrum-2.0-7B 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 are Artefact2's thoughts on the matter…
GGUF quantizations of reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT for local and edge deployment via llama.cpp and compatible runtimes. Coder teacher → STEM distillation → logical inference SFT → quantized. Structured reasoning in ~1.2GB. Stage 1 — Coder Teacher Distillation: Qwen3-1.7B distilled from Qwen3-Coder-30B-A3B-Instruct on 6,122 STEM CoT samples. Proof-weighted cross-entropy (2.5x → 1.5x on derivation tokens) + KL divergence at T=2.0. The Coder teacher transfers structured decomposition patterns — sequential logic, state tracking, compositional reasoning — through the softmax landscape. Stage 2 — Logical Inference SFT: Fine-tuned on KonstantinDob/logicinferencedataset (~54,607…
This is an efficient zero-shot classifier inspired by GLiNER work. It demonstrates the same performance as a cross-encoder while being more compute-efficient because classification is done at a single forward path. It can be used for topic classification, sentiment analysis and as a reranker in RAG pipelines. The model was trained on synthetic data and can be used in commercial applications. First of all, you need to install GLiClass library: Than you need to initialize a model and a pipeline: Below, you can see the F1 score on several text classification datasets. All tested models were not fine-tuned on those datasets and were tested in a zero-shot setting. Below you can find a comparison…
TabPFN-2.6 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass. Inference code can be found at https://github.com/PriorLabs/tabPFN. Fitting a classifier and predicting looks like this: For more examples (e.g. how to train a regressor), see the github repo: https://github.com/PriorLabs/tabPFN! Developed by Prior Labs. Regression and classification tasks with ≤50 000 samples and ≤2000 features in structured tabular format. - Not suitable for unstructured data (text, images); use API version for textual features. - Not tested for >50 000 samples or > 2000 features. Transformer with TabPFNv2-like alternating attention with…
This model is a fine-tune of the excellent tasksource/ModernBERT-large-nli, trained on the dleemiller/FineCat-NLI dataset—a compilation of several high-quality NLI data sources with quality screening and reduction of easy samples in the training split. The training also incorporates logit distillation from MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli, a top-performing NLI model, particularly on ANLI benchmarks. \begin{equation} \mathcal{L} = \alpha \cdot \mathcal{L}{\text{CE}}(z^{(s)}, y) + \beta \cdot \mathcal{L}{\text{MSE}}(z^{(s)}, z^{(t)}) \end{equation} where \\(z^{(s)}\\) and \\(z^{(t)}\\) are the student and teacher logits, \\(y\\) are the ground truth labels, and…
Blog: https://research.google/blog/videoprism-a-foundational-visual-encoder-for-video-understanding/ VideoPrism is a foundational video encoder that enables state-of-the-art performance on a large variety of video understanding tasks. It takes video frames as input and outputs compact embeddings of the frames, which one can conveniently feed into classifiers, LLMs, retrieval models, etc. When tested on 33 public video understanding benchmarks over four task categories, a single frozen VideoPrism checkpoint outperforms previous best-performing foundation models on 31 of them, with no fine-tuning on target task datasets. We release the following model variants: VideoPrism-B/L are the…
weighted/imatrix quants of https://huggingface.co/nikhilchandak/LlamaForecaster-8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/LlamaForecaster-8B-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 Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.