サイト内検索

AI モデル 2119

• mobilevit-xx-small↗

  apple

  MobileViT model pre-trained on ImageNet-1k at resolution 256x256. It was introduced in MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer by Sachin Mehta and Mohammad Rastegari, and first released in this repository. The license used is Apple sample code license. Disclaimer: The team releasing MobileViT did not write a model card for this model so this model card has been written by the Hugging Face team. MobileViT is a light-weight, low latency convolutional neural network that combines MobileNetV2-style layers with a new block that replaces local processing in convolutions with global processing using transformers. As with ViT (Vision Transformer), the image data is converted into flattened patches before it is processed by the transformer layers. Afterwards, the patches are "unflattened" back into feature maps. This allows the MobileViT-block to be placed anywhere inside a CNN. MobileViT does not require any positional embeddings.

• Viggle-Animate-ComfyUI↗

  drbaph

  ComfyUI-native conversions of **Viggle/Viggle-Animate** — a 33.1 B full finetune of MiniMax-H3's `ref2va` transformer for **character replacement in video**: a driving clip provides motion, camera, background and lighting; one reference still provides the character. No text encoder — conditioning is a frozen 362-token embedding. The sampler is DMD2-distilled: **4 steps (3 forward passes)**. **ComfyUI node pack (required for the conditioning layout):** github.com/Saganaki22/ComfyUI-Viggle-Animate-H3 - minimax_h3_ref2va_viggle_pruned_int8_convrot.safetensors (21 GB) - minimax_h3_ref2va_viggle_int8_convrot.safetensors (47 GB) - minimax_h3_ref2va_viggle_bf16.safetensors (66.3 GB, max quality)

• moonshine-streaming-small-gguf↗

  handy-computer

  Ported from upstream commit 2c03650, pinned 2026-05-06. Validated against the HF Transformers v5.7.0 reference at transcribe.cpp commit 0d312ce on 2026-05-06. English speech-to-text in both one-shot and streaming modes. An encoder-decoder ASR model designed for streaming use (ergodic encoder + sliding-window attention, 50 Hz time-domain frontend). Same family as moonshine-streaming-tiny; deeper encoder/decoder (10 / 10 layers) and wider hidden dims (encoder 620 / decoder 512). Takes a 16 kHz mono WAV and produces a transcript. No translation, no multilingual capability, no timestamps. WER on the full LibriSpeech test-clean split (2,620 utterances). Figures without a commit were published before provenance was recorded.

• Erlangshen-Roberta-110M-Sentiment↗

  IDEA-CCNL

  This is the fine-tuned version of the Chinese RoBERTa-wwm-ext-base model on several sentiment analysis datasets. Based on chinese-roberta-wwm-ext-base, we fine-tuned a sentiment analysis version on 8 Chinese sentiment analysis datasets, with totaling 227,347 samples.

• samantha-1.1-westlake-7b-GGUF↗

  MaziyarPanahi

• Nemotron-3-Embed-8B-BF16↗

  NVIDIA

  **Nemotron-3-Embed-8B-BF16** is a versatile text embedding model trained by NVIDIA and optimized for retrieval and semantic similarity tasks. It provides strong multilingual and cross-lingual retrieval capabilities and is designed to serve as a foundational component in text-based Retrieval-Augmented Generation (RAG) systems. This model was evaluated across 34 languages: English, Arabic, Assamese, Bengali, Bulgarian, Chinese, Danish, Dutch, Finnish, French, German, Hindi, Hinglish, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Nepali, Norwegian, Persian, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Ukrainian, Urdu, Vietnamese. The model generates dense vector embeddings from multilingual text inputs, enabling retrieval, semantic search, and (agentic) RAG workflows. As a core component of text retrieval systems, an embedding model transforms text, such as questions or passages, into dense vector representations. These models are typically transformer encoders that process input tokens and produce embeddings suitable for efficient similarity matching. **Nemotron-3-Embed-8B-BF16** achieves state-of-the-art performance on the multilingual RTEB leaderboard) as of July 16, 2026. Read more details in our Blog Post.

• Qwen-Drive-1.0-4B↗

  阿里巴巴 · Qwen

  > [!Note] > This repository contains the weights and configurations of Qwen-Drive-1.0 in the Hugging > Face format. The accompanying code, demo data and documentation are released at > QwenLM/Qwen-Drive-1.0. Qwen-Drive-1.0 retains the architecture of the pretrained Qwen3.5 vision-language model and integrates **3D perception**, **visual question answering**, and **motion planning** within a unified framework. The natively multimodal Qwen3.5-4B serves as the shared VLM, with two external modules attached: a **BEV perception head** jointly performing 3D object detection, semantic occupancy prediction and BEV map segmentation, and a **Planning Expert** that conditions on the shared VLM representations to generate future ego trajectories through flow matching. The unchanged VLM answers free-form questions about driving scenes. A staged training recipe combines driving supervision with general-purpose vision-language data, so the model acquires driving-specific competence while preserving broad visual understanding and instruction-following capability. With planning samples assembled purely from public sources, Qwen-Drive-1.0 unifies the trajectory format across datasets and evaluates from open-loop prediction to closed-loop driving. The SFT model is already competitive across all benchmarks. After reinforcement learning, the model trades only a marginal open-loop displacement for comprehensive gains in human-preference alignment and closed-loop safety.

• resnet10t.c3_in1k↗

  timm

  This model features: * ReLU activations * tiered 3-layer stem of 3x3 convolutions with pooling * 2x2 average pool + 1x1 convolution shortcut downsample Recipe details: * Based on ResNet Strikes Back `C` recipes * SGD (w/ Nesterov) optimizer and AGC (adaptive gradient clipping). * Cosine LR schedule with warmup

• JevK5-GGUF↗

  alibiserikbay

  GGUF builds of JevK5 (4B), JevK5-9B and JevK5-2B for llama.cpp, which runs on NVIDIA, AMD, Intel and Apple GPUs and on plain CPUs. JevK5 is an Apache-2.0 open alternative to TypeSafe's Jev. It reads a document and a yes/no, choice, or score question and returns **a probability for every option in one forward pass, with nothing generated**. It is not affiliated with TypeSafe AI. Every file was checked against its unquantized model on JevBench's 231 public decisions, scored the same way: how often it gives the same answer, and its accuracy per tier. We publish a file only if at least 95% of its answers match. **Each model has its own temperatures; pass them to the client as shown under "Run it".**

• ThonburianTTS↗

  biodatlab

  **Thonburian TTS** is a **Thai Text-to-Speech (TTS)** engine built on top of the F5-TTS. It generates **natural and expressive Thai speech** by leveraging **Flow-Matching diffusion techniques** and can **mimic reference voices** from short audio samples. The system supports: The **models** are released under the Creative Commons Attribution Non-Commercial ShareAlike 4.0 License (CC BY-NC-SA 4.0). We would like to acknowledge NSTDA Supercomputer Center (ThaiSC) project \#pv824003 for providing computing resources for this work.