전체 검색

AI 모델 449

• Hunyuan3D-2↗

  腾讯

  This repository contains the models of the paper Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation. For code and more details on how to use it, refer to the Github repository. - Jan 21, 2025: 💬 Release Hunyuan3D 2.0. Please give it a try! We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model - Hunyuan3D-DiT, and a large-scale texture synthesis model - Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio - a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and e.t.c.

• Qwen2.5-Coder-3B-Instruct-MLX-4bit↗

  lmstudio-community

  *👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. Compatibility: Apple Silicon Macs **Model creator:** Qwen **Original model**: Qwen2.5-Coder-3B-Instruct **MLX quantizations:** provided by bartowski from mlx-examples LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

• nb-wav2vec2-1b-bokmaal↗

  NbAiLab

  This model is finetuned on top of feature extractor XLS-R from Facebook/Meta. The finetuned model achieves the following results on the test set with a 5-gram KenLM. The numbers in parentheses are the results without the language model: - **WER: 0.0633** (0.0738) - **CER: 0.0248** (0.0263) This is one of several Wav2Vec-models our team created during the 🤗 hosted Robust Speech Event. This is the complete list of our models and their final scores: In parallel with the event, the team also converted the Norwegian Parliamentary Speech Corpus (NPSC) to the NbAiLab/NPSC in 🤗 Dataset format and used that as the main source for training.

• dolphin-2.8-mistral-7b-v02↗

  dphn

  My appreciation for the sponsors of Dolphin 2.8: - Crusoe Cloud - provided excellent on-demand 10xL40S node - Winston Sou - Along with a generous anonymous sponsor, donated a massive personally owned compute resource! - Abacus AI - my employer and partner in many things. This model is based on Mistral-7b-v0.2 a new base model released by MistralAI on March 23, 2024 but they have not yet published on HuggingFace. Thanks to @alpindale for converting / publishing. Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

• Meta-Llama-3.1-8B-Instruct-int8↗

  FriendliAI

  This repo contains the Llama 3 8B Instruct model quantized to INT8 by FriendliAI, significantly enhancing its inference efficiency while maintaining high accuracy. Check out FriendliAI documentation for more details. 1. Sign in Friendli Suite. 2. Go to **User Settings > Tokens** and click **'Create new token'**. 3. Save your created token value. Container secret is a credential to launch our Friendli Container images. You should pass the container secret as an environment variable to run the container image.

• pony-v7-base↗

  Runware

  Pony V7 is a versatile character generation model based on AuraFlow architecture. It supports a wide range of styles and species types (humanoid, anthro, feral, and more) and handles character interactions through natural language prompts. First, let me introduce Fictional - our multimodal platform where AI Characters come alive through text, images, voice, and (soon) video. Powered by PonyV7, V6, Chroma, Seedream 4, and other advanced models, Fictional lets you discover, create, and interact with characters who live their own lives and share their own stories. Fictional is also what enables the development of models like V7, so if you're excited about the future of multimodal AI characters, please download Fictional on iOS or Android and help shape our future!

• GLuCoSE-base-ja↗

  pkshatech

  GLuCoSE (General LUke-based COntrastive Sentence Embedding, "glucose") is a Japanese text embedding model based on LUKE. In order to create a general-purpose, user-friendly Japanese text embedding model, GLuCoSE has been trained on a mix of web data and various datasets associated with natural language inference and search. This model is not only suitable for sentence vector similarity tasks but also for semantic search tasks. - Maximum token count: 512 - Output dimension: 768 - Pooling: mean pooling - Supported language: Japanese You can use this model easily with sentence-transformers. Since the loss function used during training is cosine similarity, we recommend using cosine similarity for downstream tasks.

• llama-3-merged-linear↗

  uygarkurt

  In this specific case, I typed `llama-3` into the open LLM leaderboard, took the best 3 models, merged them and created a better ranking model wihtout any training.

• Singularity-LTX-2.3_OmniCine_V1↗

  WarmBloodAban

  This is not just a standard fine-tune; it is a fundamental restructuring of the **LTX-Video (2.3)** generation logic. I am thrilled to present the official release of **LTX2.3 Singularity** to the community. This comprehensive optimization framework focuses heavily on **Image-to-Video (I2V)**, **First & Last Frame Control**, and **Reference-to-Video** generation. Although it has currently undergone only nearly **100,000 steps** (calculated by gradient accumulation), its enhancements in physical consistency, dynamic motion, and cinematic expression have already far exceeded expectations. 您的浏览器不支持视频标签。 Prompt:8-second video, one-take shot,this high-octane cinematic animation features a young woman skateboarding down a steep coastal road during a bright, sunny afternoon, evoking a sense of freedom and adrenaline. From 0 to 3 seconds, the girl crouches low on her skateboard, her long brown hair streaming behind her as she accelerates down the incline. Between 4 and 8 seconds, she maintains a steady, aerodynamic posture, skillfully navigating the winding asphalt while her oversized white t-shirt billows in the wind, showing intense focus and excitement. The camera utilizes a low-angle tracking shot from directly behind the skater, moving at a high velocity to create an immersive sense of speed; the composition starts with a wide-angle view of the sprawling coastal city and ocean, then maintains a medium-close-up on the girl's back and the board throughout the descent. The setting is a picturesque Mediterranean-style hillside overlooking a turquoise bay under a vibrant blue sky filled with fluffy white clouds, featuring high-contrast sunlight casting sharp shadows and a warm, high-saturation color palette. The soundscape is dominated by the continuous, high-pitched whirring of skateboard wheels against the pavement and the rushing sound of wind, synchronized with an upbeat, rhythmic electronic background track. Significant motion blur is applied to the road surface and passing scenery to enhance the perception of speed, combined with a sharp focus on the central subject to maintain a polished, professional look，无字幕。 您的浏览器不支持视频标签。 Prompt:Modern anime style, office sett

• gemma-3-12b-it-bnb-4bit↗

  unsloth

  Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components: The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats.