Open-Weight Models

Model

dhcp-ours-coco-llava15-13b

Đinh Quốc Bảo

Object-hallucination probe trained on a LLaVA-1.5-13B COCO corpus, with three independent training seeds (0, 42, 1337). It is not interchangeable with the 7B release: features, geometry and thresholds are model-specific. 10,000 COCO train2014 images split 80/20 by image: 8,000 train / 54,253 object spans and 2,000 holdout / 13,789 object spans. Captions are generated by 13B itself, so this corpus is not the 7B corpus. Thresholds are selected by best F1 on the COCO validation split and then frozen. Nothing is tuned on the test holdout, AMBER, or POPE. COCO test holdout — mention view, n=13,787, 16.19% positive AMBER, strict zero-shot — n=2,367 rows / 977 images, 5.37% positive, COCO…

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).…

Model · Text generation

diakosmos

Ajax Davis

Diakosmos (διάκοσμος, "the ordering of a world") is a byte-level harmonic recurrent language model, 99,823,934 parameters, written and trained from scratch in the Alpha language on a rented RTX 3070. It has no tokenizer and no attention matrix: each byte enters as a fixed constellation of phasors (the wiretable), and each of 14 blocks blends a decaying harmonic recurrence over the past with a planar rotation between seven wire groups. Its design is harmonic-gpt's leading model. The tensors carry harmonic-gpt's parameter names; wiretable is the fixed byte encoding (256 x 1330). updates of 64 windows, 24.5 GPU hours and 5.29 kWh on one RTX 3070. Held-out OpenWebText: 1.4194 bits per byte…

Model · Token classification

dialect-spot

GoldReal AI

Scores words for association with US, British, Australian and New Zealand English. Linear heads on a frozen encoder. Each word has character offsets, per-region probabilities and regions (regions above the calibrated threshold). Pass spans=[[(start, end),...]] to score phrases instead of single words.

Unconditional and conditional DDPM training artifacts for CIFAR-10, using custom UNet architectures with attention and EMA. Only the final unconditional and conditional checkpoints are published: - ddpmwithattentionema/checkpoints/ddpmfinal.pt - conditionalddpmwithattentionema/checkpoints/conditionalddpmfinal.pt Each file is about 3.11 GiB, about 6.2 GiB combined. Intermediate checkpoints, sample images, and training history CSV files are not published. The original full final checkpoints contain model, EMA model, optimizer, scheduler, epoch, and loss state. Use emamodelstatedict for EMA inference weights, with the matching custom architectures from the code repository. Download the…

Model · Robotics

diffusion_blocos_pote

Victor Ivar van Halst

Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot 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 calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…

Model

dino-baseline

Cheng Chen

A research-oriented Dino prototype targeting Matching. The included large setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lion with a constant warmup schedule. These are starting values in the script, not evidence of a completed run. For a…

Model

dino-classification6

Pedro

A research-oriented Dino prototype targeting Classification. The included xlarge setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adamw with a cosine schedule. These are starting values in the script, not evidence of a completed run. For a…

Model

dino-demo

Krish

A research-oriented Dino prototype targeting Retrieval. The included nano setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses novograd with a onecycle schedule. These are starting values in the script, not evidence of a completed run. For a…

Model

dino-experiment

Mark Deboer

A research-oriented Dino prototype targeting Classification. The included nano setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lion with a polynomial schedule. These are starting values in the script, not evidence of a completed run. For a…

Model

dino-experiment81

Rikukatoora

A small Dino implementation for Multitask, packaged with an explicit configuration and an initialization checkpoint. The xlarge variant is a reproducible starting point, not a trained model release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adamw with a step schedule. These are starting values in the script, not evidence of a…

Model

dino-generation

S. Young

Working implementation of Dino for Generation using a small configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses rmsprop with a exponential schedule. These are starting values in the script, not evidence of a…

Model

dino-generation28

Joshua Johnson

Working implementation of Dino for Generation using a small configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses lion with a step schedule. These are starting values in the script, not evidence of a completed…

Model

dino-retrieval69

Christopher Garcia

Working implementation of Dino for Retrieval using a base configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adamw with a constant warmup schedule. These are starting values in the script, not evidence of a…

训练时对文本做了规范化（还原 HTML 转义、链接替换为 http），推理时建议做同样的处理， 见项目中的 triage/preprocess.py。 - 数据：Kaggle NLP with Disaster Tweets 的 train.csv，其中 id ≤ 8696 的 6090 条用于训练，其余 1523 条作为验证集。 - 超参数：BERT 学习率 2e-5，ModernBERT 学习率 5e-5；2 个 epoch；batch size 32；maxseqlength 128； weight decay 0.01；warmup 0.1；bf16；随机种子 42。 同一配置 3 个随机种子的 Macro-F1：BERT 81.63 ± 0.11，ModernBERT 81.70 ± 1.11，两者的差异在种子波动范围内。 - 仅支持英文；比喻性用法（如 "this mixtape is fire"）仍可能误判。 - 两个模型都只在推文（≤ 82 token）上微调，ModernBERT 在长文本上的效果没有经过标注数据验证。 - 模型权重：CC BY-NC 4.0。基于 Kaggle 比赛数据训练，仅限非商业用途；使用时还需遵守该比赛规则中对数据的限制。 - 基础模型：bert-base-uncased、ModernBERT-base（均为 Apache-2.0）。

本仓库包含 5 个基于 π0.5 的洗碗机餐盘操作 checkpoint。它们均使用 16 维直接动作表示（actiondim=32，包含双臂），动作预测 horizon 为 50；训练产物采用 JAX/Orbax checkpoint 格式。 circleLupload、circleMupload、squareupload 和 mixupload 是视觉-触觉策略。它们使用冻结的 facebook/sparsh-vjepa-base 作为触觉编码器，输入为相对于每个 episode 第 0 帧生成的 4 帧有序背景差分触觉序列： mixunload 不使用触觉输入或触觉编码器；它使用常规视觉/状态输入，并同样使用最近 8 步动作历史进行条件化。 - 五个顶层模型目录采用一致的结构：目录本身就是可加载的 Orbax checkpoint 根目录，下面直接包含 CHECKPOINTMETADATA、params/ 和 assets/。 - 每个 checkpoint 中的 assets//normstats.json 保存对应训练数据的归一化统计量；加载时应与同一 checkpoint 配套使用。 - circleLupload, circleMupload, squareupload, and mixupload are tactile π0.5 policies for loading large round, medium round, square, and mixed plates into a dishwasher rack, respectively. They…

Model

dissertation-contrastive-2024

Laura Garnier

Working implementation of Mae for Contrastive using a nano configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adam with a polynomial schedule. These are starting values in the script, not evidence of a…