Open-Weight Models Under Apache License 2.0

本仓库提供由 depth-anything/DA3-BASE 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-DEPTH-DA3-BASE - 模型显示名称：RK182X-DEPTH-DA3-BASE - 源模型：depth-anything/DA3-BASE - 模型类型：DEPTH ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 Qwen/Qwen3-Embedding-4B 转换得到的 RKNN EMBEDDING 模型。 - Model ID：RKNNAI/RK182X-EMBEDDING-Qwen3-Embedding-4B - 模型显示名称：RK182X-EMBEDDING-Qwen3-Embedding-4B - 源模型：Qwen/Qwen3-Embedding-4B - 模型类型：EMBEDDING ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 Qwen/Qwen3-Reranker-0.6B 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-EMBEDDING-Qwen3-Reranker-0.6B - 模型显示名称：RK182X-EMBEDDING-Qwen3-Reranker-0.6B - 源模型：Qwen/Qwen3-Reranker-0.6B - 模型类型：EMBEDDING ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 openbmb/MiniCPM5-1B 转换得到的 RKNN LLM 模型。 - Model ID：RKNNAI/RK182X-LLM-MiniCPM5-1B - 模型显示名称：RK182X-LLM-MiniCPM5-1B - 源模型：openbmb/MiniCPM5-1B - 模型类型：LLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。 本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

本仓库提供由 openbmb/MiniCPM5-2B 转换得到的 RKNN LLM 模型。 - Model ID：RKNNAI/RK182X-LLM-MiniCPM5-2B - 模型显示名称：RK182X-LLM-MiniCPM5-2B - 源模型：openbmb/MiniCPM5-2B - 模型类型：LLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。 本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

本仓库提供由 Qwen/Qwen2.5-0.5B-Instruct 转换得到的 RKNN LLM 模型。 - Model ID：RKNNAI/RK182X-LLM-Qwen2.5-0.5B-Instruct - 模型显示名称：RK182X-LLM-Qwen2.5-0.5B-Instruct - 源模型：Qwen/Qwen2.5-0.5B-Instruct - 模型类型：LLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。 本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

本仓库提供由 Qwen/Qwen3-1.7B 转换得到的 RKNN LLM 模型。 - Model ID：RKNNAI/RK182X-LLM-Qwen3-1.7B - 模型显示名称：RK182X-LLM-Qwen3-1.7B - 源模型：Qwen/Qwen3-1.7B - 模型类型：LLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 google/gemma-4-E2B-it 转换得到的 RKNN MLLM 模型。 - Model ID：RKNNAI/RK182X-MLLM-Gemma-4-E2B-it - 模型显示名称：RK182X-MLLM-Gemma-4-E2B-it - 源模型：google/gemma-4-E2B-it - 模型类型：MLLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 Qwen/Qwen3-TTS-12Hz-0.6B-Base 转换得到的 RKNN TTS 模型。 - Model ID：RKNNAI/RK182X-TTS-Qwen3-TTS-12Hz-0.6B-Base - 模型显示名称：RK182X-TTS-Qwen3-TTS-12Hz-0.6B-Base - 源模型：Qwen/Qwen3-TTS-12Hz-0.6B-Base - 模型类型：TTS ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型采用 Apache License 2.0，正文见 LICENSE，归属和转换说明见 NOTICE。同时遵守 RKNN Toolkit 和 RKNN Runtime 相关许可。

本仓库提供由 Qwen/Qwen3-TTS-12Hz-1.7B-Base 转换得到的 RKNN TTS 模型。 - Model ID：RKNNAI/RK182X-TTS-Qwen3-TTS-12Hz-1.7B-Base - 模型显示名称：RK182X-TTS-Qwen3-TTS-12Hz-1.7B-Base - 源模型：Qwen/Qwen3-TTS-12Hz-1.7B-Base - 模型类型：TTS ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 facebookresearch/dinov2 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-dinov2vits14 - 模型显示名称：RK182X-VIT-dinov2vits14 - 源模型：facebookresearch/dinov2 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 google/siglip-so400m-patch14-384 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-siglip-so400m-patch14-384 - 模型显示名称：RK182X-VIT-siglip-so400m-patch14-384 - 源模型：google/siglip-so400m-patch14-384 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 google/siglip2-so400m-patch14-384 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-siglip2-so400m-patch14-384 - 模型显示名称：RK182X-VIT-siglip2-so400m-patch14-384 - 源模型：google/siglip2-so400m-patch14-384 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 google/vit-base-patch16-224 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VIT-vit-base-patch16-224 - 模型显示名称：RK182X-VIT-vit-base-patch16-224 - 源模型：google/vit-base-patch16-224 - 模型类型：VIT ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

本仓库提供由 OpenGVLab/InternVL3-2B 转换得到的 RKNN VLM 模型。 - Model ID：RKNNAI/RK182X-VLM-InternVL3-2B - 模型显示名称：RK182X-VLM-InternVL3-2B - 源模型：OpenGVLab/InternVL3-2B - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。 本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

本仓库提供由 OpenDataLab/MinerU2.5-Pro-2604-1.2B 转换得到的 RKNN VLM 文档解析模型。官方模型为 1.2B 参数的图文到文本模型，可用于文档版面、文本、公式和表格内容解析；官方权重采用 Apache License 2.0。Hugging Face 模型页。 - Model ID：RKNNAI/RK182X-VLM-MinerU2.5-Pro-2604-1.2B - 模型显示名称：RK182X-VLM-MinerU2.5-Pro-2604-1.2B - 源模型：OpenDataLab/MinerU2.5-Pro-2604-1.2B - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 提供单图文档识别模型；完整 PDF 解析流程需由应用实现。 源模型采用 Apache License 2.0，正文见 LICENSE，来源与转换说明见 NOTICE。同时遵守 RKNN Toolkit 和 RKNN Runtime 的相关许可。

本仓库提供由 Qwen/Qwen2.5-VL-3B-Instruct 转换得到的 RKNN VLM 模型。 - Model ID：RKNNAI/RK182X-VLM-Qwen2.5-VL-3B-Instruct - 模型显示名称：RK182X-VLM-Qwen2.5-VL-3B-Instruct - 源模型：Qwen/Qwen2.5-VL-3B-Instruct - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 Qwen/Qwen3.5-0.8B 转换得到的 RKNN VLM 模型。 - Model ID：RKNNAI/RK182X-VLM-Qwen3.5-0.8B - 模型显示名称：RK182X-VLM-Qwen3.5-0.8B - 源模型：Qwen/Qwen3.5-0.8B - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 Qwen/Qwen3.5-2B 转换得到的 RKNN VLM 模型。 - Model ID：RKNNAI/RK182X-VLM-Qwen3.5-2B - 模型显示名称：RK182X-VLM-Qwen3.5-2B - 源模型：Qwen/Qwen3.5-2B - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 Qwen/Qwen3-VL-2B-Instruct 转换得到的 RKNN VLM 模型。 - Model ID：RKNNAI/RK182X-VLM-Qwen3-VL-2B-Instruct - 模型显示名称：RK182X-VLM-Qwen3-VL-2B-Instruct - 源模型：Qwen/Qwen3-VL-2B-Instruct - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本仓库提供由 HuggingFaceTB/SmolVLM-500M-Instruct 转换得到的 RKNN VLM 模型。 - Model ID：RKNNAI/RK182X-VLM-SmolVLM-500M-Instruct - 模型显示名称：RK182X-VLM-SmolVLM-500M-Instruct - 源模型：HuggingFaceTB/SmolVLM-500M-Instruct - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。 本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

本仓库提供由 ByteDance-Seed/UI-TARS-2B-SFT 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-VLM-UI-TARS-2B-SFT - 模型显示名称：RK182X-VLM-UI-TARS-2B-SFT - 源模型：ByteDance-Seed/UI-TARS-2B-SFT - 模型类型：VLM ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。

This repository provides RKLLM deployment configurations of Qwen3-4B-Instruct-2507 for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration.

This repository provides RKLLM deployment configurations of Qwen3.5-2B for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The source model is Qwen/Qwen3.5-2B, licensed under the Apache License 2.0. See LICENSE. Original copyright notices are retained in the license file. This distribution converts and quantizes the language model to RKLLM format for RK3576.

This repository provides RKNN deployment configurations of MobileSAM for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The model is provided through RKNN Model Zoo and originates from airockchip/MobileSAM. The upstream license is Apache License 2.0; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file. This distribution converts the source model to RKNN format for RK3576, using the precision specified in each configuration.

This repository provides RKNN deployment configurations of ppliteseg-cityscapes for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The model is provided through RKNN Model Zoo and originates from PaddlePaddle/PaddleSeg. The upstream license is Apache License 2.0; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file. This distribution converts the source model to RKNN format for RK3576, using the precision specified in each…

This repository provides RKNN deployment configurations of dinov2vitb14 for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. Source project: dinov2vitb14. License: apache-2.0; see LICENSE. This distribution contains RKNN conversion derivatives for RK3576. See NOTICE for attribution.

This repository provides RKNN deployment configurations of dinov2vits14 for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. Source project: dinov2vits14. License: apache-2.0; see LICENSE. This distribution contains RKNN conversion derivatives for RK3576. See NOTICE for attribution.

This repository provides RKNN deployment configurations of LightGlue for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. Source project: LightGlue. License: apache-2.0; see LICENSE. This distribution contains RKNN conversion derivatives for RK3576.

We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements: - Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. - Substantial gains in long-tail knowledge coverage across multiple languages. - Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation. - Enhanced capabilities in 256K long-context understanding. Qwen3-4B-Instruct-2507 has the following features: NOTE: This model supports only non-thinking…

Model

RLCD-Qwen3.5-9B-Gated-Decision

SourceHat Labs

SourceHat RLCD is a research model for bounded decisions: commit to one complete object, return alternatives, or abstain. A frozen Qwen3.5-9B text backbone represents context, evidence, and supplied choices in one shared forward pass. Small learned heads score the choices and their combinations; a calibrated policy selects an operating mode. This is not a conversational model or an arbitrary JSON generator. It is designed for classification and routing experiments where the caller defines the candidate choices, validates the result, and retains a verifier or human fallback. It executes no external action. On the main synthetic test, 46 of 49 commitments were correct, out of 250 total cases…

Training run started on 2026-09-18. Training is in progress; no quality evaluation is claimed. - RLOO, learning rate 1e-6, KL coefficient 0, sigmoid length reward alpha 0.1, seed 79. - Sampling temperature 1.0, top-p 1.0. No validation run. - Synchronous generation/training on the same eight H100 80GB GPUs; ZeRO-2; bfloat16. Every 20 rollout steps, a resumable DeepSpeed checkpoint (model and optimizer state) is uploaded under checkpoints/actor/globalstepN/, together with its training configuration. It is not a standalone Transformers model folder. Restore that directory and a latest file containing its tag to resume with the same OpenRLHF configuration. Local files are removed only after…

Base: google/gemma-4-12B-it, loaded text-only (the decoder of the unified multimodal checkpoint; see scripts/port/maketextonlyckptgemma4.py). Adapter: LoRA r32, alpha 32, on q/o/gate/up/down (all 48 layers) + k/v (the 40 sliding-window layers). Standard PEFT format: PeftModel.frompretrained(, repo, subfolder=...). Thinking uses Gemma's thought... channel (rewardlaundering/gemma4renderer.py), temperature 1.0, think budget 2500. Research checkpoint from the reward-laundering project ("ext-model": does owned-haiku reward laundering replicate on a non-Qwen model family?). Full write-up: results/EXTMODEL.md. Held-out haiku = evalpropensity --trait haiku --locus response, 16 neutral prompts x 8…

Base: google/gemma-4-12B-it, loaded text-only (the decoder of the unified multimodal checkpoint; see scripts/port/maketextonlyckptgemma4.py). Adapter: LoRA r32, alpha 32, on q/o/gate/up/down (all 48 layers) + k/v (the 40 sliding-window layers). Standard PEFT format: PeftModel.frompretrained(, repo, subfolder=...). Thinking uses Gemma's thought... channel (rewardlaundering/gemma4renderer.py), temperature 1.0, think budget 2500. Research checkpoint from the reward-laundering project ("ext-model": does owned-haiku reward laundering replicate on a non-Qwen model family?). Full write-up: results/EXTMODEL.md. Held-out haiku = evalpropensity --trait haiku --locus response, 16 neutral prompts x 8…

İpek Öztaş, Duygu Ceylan, Aybars Buğra Aksoy, Ayşegül Dündar This repository contains the RoPEMover LoRA (rank 16) for RoPEMover moves an object in a single image by manipulating a depth-aware 3D extension of the diffusion transformer's rotary positional embeddings. This LoRA requires the modified pipeline from the RoPEMover code repository. It does not work with the stock Qwen-Image-Edit pipeline. The weights are downloaded from this repository automatically. Apache 2.0. Use is also subject to the license of

A LoRA adapter for Qwen/Qwen3.5-4B that turns an outing's facts into a short card in Telugu for a parent who is visiting family abroad: where they're going, when, how to get there and back, and one thing they'll like. It is the card writer of Roundtrip, a planner that helps visiting parents get out to real places on their own. Cards are coastal Andhra (Guntur) Telugu, warm and respectful (మీరు forms, అమ్మా for a mother and నాన్నగారు for a father), 60 words or fewer, with every bus, street, stop and venue name kept in English letters so it matches the signs. - 342 training cards for 360 synthetic outings, and 40 more outings held out for evaluation. - Venues, bus lines and stop names come…

trained option-scoring head. It answers choice / noul / score questions about a document and up to four images in one forward pass, and speaks the Images need the vision extra (Pillow, torchvision): pip install "rsi-jev[vision] @ git+https://github.com/Shanghua-Gao/RSI-Jev". The vision encoder and image processor are read from the base model. This checkpoint (seed 17, one seed): Re-computed from these exact files after upload-time reload. Kernel stack fla-0.5.2/torch-2.7.1+cu128; full recipe in meta.json. loadrelease applies calibration.safetensors when the checkpoint carries one, so the probabilities are the calibrated ones this card reports. A loader that skips those files returns the raw…

Model · Image and text to text

RSR-27B

Agent Intelligence-Lab

RSR-27B is Qwen-3.8-27B finetuned with Recursive Self-Rewrite (RSR) trajectories.

Model · Text classification

RubriX-8B

CobuildX AI

RubriX is a non-autoregressive rubric judge. Given a criterion, the rubric's level descriptions and a response (optionally with the conversation it answers), it returns a probability for every level in a single pass, with no text generation. Level descriptions are embedded once per rubric and cached, so the cost of each judgment does not grow with the number or length of the levels. Read more in the blog post: Introducing RubriX. One encoder, Qwen3-8B with this repository's LoRA adapter, embeds the input and each level description separately. Two projection heads map them into a shared space, and - sk = τ · cos(f(input), g(levelk)), with τ = 100 - p = softmax(s1 … sK) The model was trained…

static quants of https://huggingface.co/ritiksuman/rudra For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/rudra-i1-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…

weighted/imatrix quants of https://huggingface.co/ritiksuman/rudra For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/rudra-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…

This model is a LoRA finetuned Qwen model that employs production rules to ensure strictt rule compliance with Grade2 Braille rules and outperforms a neural-only model on UEB compliance metrics like compliance, capitalization, punctuation, numeric, and OOV accuracy. These individual metrics form the model's recall. The precision score of the model (accounts for character insertions in the outputs differing from references) is also way better than the stand-alone neural model.

Model

S-AGI

Convergent Intelligence

Part of the Standalone Models by Convergent Intelligence LLC: Research Division 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 singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as structural signals that reveal the geometry of the learning problem. Key concepts: For the full mathematical treatment, see Discrepancy Calculus: Foundations and Core…

s1 is an open, calibrated System One decision model. Given a state (text or JSON) and a typed question, it returns a probability for every option in one forward pass, with no text generated: It is google/gemma-4-26B-A4B-it (mixture of experts, 26B total and about 4B active parameters) fine-tuned with LoRA on about 100,000 typed decision rows, and merged. Code, data and Held-out test sets. The released snapshot was chosen on separate dev splits by a rule fixed before training. - Mean accuracy over JevBench's 11 accuracy slices; ECE with 10 bins. Raw ECE is 0.083 (Jev: 0.081). - Paired against the untuned model on the same JevBench cases: 103 answers fixed, 58 broken (McNemar p = 0.0005).…

Model · Text classification

s1-jev-cvltist

CVLT AI

A local, open, Jev-compatible "System One" decision model. s1-jev-cvltist is the name of this release model (project codename "system one", s1; the internal checkpoint id is s1-v6). Base: Qwen3.5-4B (Apache-2.0) · Adapter: LoRA r=16, α=32 · Context: 4096 Interface: the TypeSafe Jev wire spec (choice / score / noul) · Size: 124 MB adapter system one (s1) is a small decision model trained to answer Jev-style questions (choice, score, noul) over a free-form "state", returning calibrated probabilities rather than a bare answer. It is deliberately built on a general instruction base (Qwen3.5-4B) with a thin LoRA adapter, so it carries knowledge a purpose-built encoder can't, while the readout…

Model · Text classification

s1-jev-cvltist

A. E. E. Collier

A local, open, Jev-compatible "System One" decision model. s1-jev-cvltist is the name of this release model (project codename "system one", s1; the internal checkpoint id is s1-v6). Base: Qwen3.5-4B (Apache-2.0) · Adapter: LoRA r=16, α=32 · Context: 4096 Interface: the TypeSafe Jev wire spec (choice / score / noul) · Size: 124 MB adapter system one (s1) is a small decision model trained to answer Jev-style questions (choice, score, noul) over a free-form "state", returning calibrated probabilities rather than a bare answer. It is deliberately built on a general instruction base (Qwen3.5-4B) with a thin LoRA adapter, so it carries knowledge a purpose-built encoder can't, while the readout…

Model

Sage-Attention-and-Sparge-Attention-HSWQ

GJL

This repository contains unofficial Windows wheels for Sage-Attention 2.2＆3-1.0, Sparge-Attention-HSWQ 1.0, compiled with CUDA 13.2. Python 3.13 (cp313) Python 3.14 (cp314) https://github.com/ussoewwin/ComfyUI-DistorchMemoryManager https://github.com/ussoewwin/SpargeAttn-hswq

Model · Text to image

Sakura-Iris-3B-GGUF

Sakura

Community quantization of speridlabs/iris-3b (3 B parameter pixel-space diffusion transformer, no VAE) for stable-diffusion.cpp, used with the official Qwen3-VL-4B-Instruct text encoder. Independent work, not made or endorsed by speridlabs or Alibaba/Qwen. Apache-2.0. Image model Q80 (Sakura-Iris-3B-Q80-4.15GiB.gguf) and the official Qwen3-VL-4B-Instruct Q80 text encoder, stable-diffusion.cpp (Vulkan, Radeon 8060S), 1024x1024, 30 steps, CFG 3, dpm++2m. One seed per prompt, all nine prompts are shown, no re-rolls and no selection. About 213 to 738 s per image including model loading (the spread comes from other jobs running on the same GPU; the fastest image is the undisturbed one); the…

Model · Text generation

Sakura-K2-Horizon-0.9B-GGUF

Sakura

K2-Horizon-0.9B is the smallest member of IFM's open K2-Horizon family: a tiny decoder-only reasoning and agent model with a long context window (Apache-2.0, fully open training data and recipe). This repository holds three GGUF files of different size made from the BF16 weights with our measured mixed-codec method. Pick one on the Files page; the table below says what each file is. Independent community quantization, not an official IFM (MBZUAI Institute of Foundation Models) release. Part of the Sakura Mini line. Same method, same texts, same machine for every file; lower KL divergence means closer to the BF16 original: - Sakura-K2-Horizon-0.9B-0.40GiB.gguf vs llama.cpp default IQ3XXS…

Model repository for SAM 2++: Tracking Anything at Any Granularity, a unified video tracking framework that extends the SAM 2 model to track any targets in videos at any granularity, including masks, bounding boxes, and points. See the SAM 2++ paper for more information. Models can alternatively be loaded from Hugging Face

The tool picker inside Turing 5.0. Samantha reads one sentence and picks one of her tools on your Mac, with the words to run it on, as one JSON line: {"tool": "openapp", "arg": "Safari"}. If the sentence is not a command, she says so: {"tool": null, "arg": ""}. Qwen2.5-1.5B-Instruct, fine-tuned on Kaggle (SFT, then a gentle DPO stage), quantized to 4 bits for Apple Silicon with mlx-lm. About 850 MB. She never runs a pick on her own say-so. Every pick goes through Turing's guard, which checks that the argument was copied from the sentence and that the sentence is really about that tool, and anything that writes asks first. Measured on sentences she never trained on: under 10 wrong picks past…

samai-27b（Qwen/Qwen3.8-27B 手术版：PonderNet 停机位点 L35/39/43/47/51/55/59/63 + dMoE 8 专家 + MTP）经 QLoRA SFT 后，按 mixbit 静态化管线产出的 llama.cpp 混合精度权重。 等价稠密模型 ≙ Qwen35ForCausalLM（48 linearattention + 16 fullattention，hidden 5120），可直接用上游 llama.cpp 载入。 - Token embedding / output：Q6K（--token-embedding-type Q6K） OpenAI 兼容端点 /v1/chat/completions。 - 基座：tchbcb/samai-27b（含 SFT adapter / 训练日志 / 数据） - 配方参考：tchbcb/samai-4b-mixbit