Open-Weight Models

Model

scFM-dataselection

Microsoft

Model checkpoints and PCA components for Evaluating the role of pretraining dataset size and diversity on single-cell foundation model performance, DenAdel et al., Nature Methods (2026). The full download is approximately 32.1 GB: 492 neural network checkpoints and 80 PCA component matrices. The neural checkpoints include 12 controls with 0% pretraining. The Geneformer, scVI and SSL models cover random sampling, cell-type reweighting and geometric sketching at 1, 10, 25, 50, 75 and 100 percent of the pretraining corpus. The collection also includes perturbation spike-in experiments. See model-index.csv for model folders and training settings. Use Python 3.10. The examples below were tested…

Research artifacts for the paper "Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling" (arXiv:2608.02829, v3; v1–v2 carried the title "What Transfers Between Transformer Sizes — and What Doesn't"). The paper asks whether a pretrained large model can be converted into a smaller sibling instead of training the small size from scratch. These checkpoints are the endpoints of matched-budget recovery races: every arm gets the same target shape, data order, schedule, and token budget, and only the starting weights differ. The initializations compared: All files are plain PyTorch statedicts for GPTNeoXForCausalLM with the target size's stock Pythia config. They are…

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).

ACCV 2026 · Gyeonggwan Lee, Eunsoo Im, Seunghwan Hong, Junghun Suh (Kakao Mobility Corp., Korea University) Pretrained SCCM weights for the main results of the paper (Tab. 1 and the SCCM row of Tab. 2). SCCM makes the coarse stage of a dense matcher sphere-aware for 360° equirectangular (ERP) images, and is instantiated in the RoMa V1 framework. Each file is a torch.save dict holding the model weights under the model key (optimizer state removed). mp3d/sccm.pth is trained on Matterport3D (indoor) and is also the model evaluated zero-shot on Stanford2D3D (indoor, Tab. 1b). holo360d/sccm.pth starts from it and is trained on Holo360D (outdoor, in-the-wild). The baseline rows of the paper…

Model · Image segmentation

sceneseg-p150

Hyunggi Chang

SceneSeg (Autoware VisionPilot): the scene segmentation network of the Autoware Foundation's VisionPilot camera stack, as its scenesegmodel node deployed it, ported to one Tenstorrent Blackhole p150 with tt-nn. One camera image of any size in (converted to BGR8, as the node receives it); the VisionPilot foreground mask (mono8, 255 = foreground, at the input's size) and a 3-class map (background / foreground / road) out, with the node's exact pre- and post-processing. Weights: weights/ of this repo @ a6829b24 (VisionPilot's SceneSegFP32.onnx and its.pth as safetensors, re-hosted from the upstream Google Drive links) · Paper: none (model card AutowareFoundation/SceneSeg) · Autoware package…

SCM ("Sovereign Classification Model", repository rev) makes typed, non-generative decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a state. This repo holds a LoRA adapter only (adaptermodel.safetensors) for Qwen/Qwen3-14B-Base at revision 0b0bd3732e2c374d483664439ea334928b65f304. It is an experimental research release, not a production model. All options of one question are shown in one prompt as lettered lines; the model's score for an option is the next-token logit of its letter. Several option orders are scored and their per-order log-softmax over the letters is averaged, then renormalised to a probability vector. The exact…

SCM ("Sovereign Classification Model") makes typed decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a text. This repo holds a LoRA adapter only for Qwen/Qwen3-14B-Base at revision 0b0bd3732e2c374d483664439ea334928b65f304 (training run s88-v1max-H100x2-20261015-113714; lr 5e-5 (bf16, 2 GPUs data-parallel), LoRA r=16 / alpha=32 on all attention and MLP projections, 16 questions per step, one epoch, prompts left-truncated at 3,072 tokens). It is not a production model. All options of one question appear in one prompt as labelled lines; the score of an option is the next-token logit of its label. Labels are A to T, then U to Z, then…

SCM ("Sovereign Classification Model", repository rev) makes typed, non-generative decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a state. This repo holds a LoRA adapter only (adaptermodel.safetensors) for Qwen/Qwen3-4B-Base at revision 906504ac4b72e133a613011318afd8206fb5e8ec. It is an experimental research release, not a production model. All options of one question are shown in one prompt as lettered lines; the model's score for an option is the next-token logit of its letter. Several option orders are scored and their per-order log-softmax over the letters is averaged, then renormalised to a probability vector. The exact…

SCM ("Sovereign Classification Model") makes typed decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a text. This repo holds a LoRA adapter only for Qwen/Qwen3-4B-Base at revision 906bfd4b4dc7f14ee4320094d8b41684abff8539 (training run s88-v1mid-H100-20261015-113727; lr 1e-4 (fp16, 1 GPU), LoRA r=16 / alpha=32 on all attention and MLP projections, 16 questions per step, one epoch, prompts left-truncated at 3,072 tokens). It is not a production model. All options of one question appear in one prompt as labelled lines; the score of an option is the next-token logit of its label. Labels are A to T, then U to Z, then single-token…

SCM ("Sovereign Classification Model", repository rev) makes typed, non-generative decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a state. This repo holds a LoRA adapter only (adaptermodel.safetensors) for Qwen/Qwen3-1.7B-Base at revision ea980cb0a6c2ae4b936e82123acc929f1cec04c1. It is an experimental research release, not a production model. All options of one question are shown in one prompt as lettered lines; the model's score for an option is the next-token logit of its letter. Several option orders are scored and their per-order log-softmax over the letters is averaged, then renormalised to a probability vector. The exact…

LoRA adapter (rank 32) on Qwen/Qwen3.5-4B, trained with the scottyrl framework for 11-768 (AI Agents, CMU), Assignment 3. - runname: p5textcraftgrpo Graders serve the adapter with vLLM and run the course evaluation script against the server, on the medium and hard TextCraft-Synth validation

Model

scratch-nmt-en-de

Five Creators Group

Best checkpoints for 4 Scratch NMT architectures on English->German (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.

Model

scratch-nmt-en-es

Five Creators Group

Best checkpoints for 4 Scratch NMT architectures (Transformer, Mamba, LSTM-Luong, GRU-Luong) on English->Spanish (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.

Model

scratch-nmt-en-fr

Five Creators Group

Best checkpoints for 4 Scratch NMT architectures on English->French (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.

Model

scratch-nmt-en-ru

Five Creators Group

Best checkpoints for 4 Scratch NMT architectures on English->Russian (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.