전체 검색

AI 모델 450

• Wan2.1_T2V_14B_FusionX-GGUF↗

  QuantStack

  All quantized versions were created from the base T2V FP16 model using the conversion scripts provided by city96, available at the ComfyUI-GGUF GitHub repository. The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders:

• mbart-large-50↗

  facebook

  mBART-50 is a multilingual Sequence-to-Sequence model pre-trained using the "Multilingual Denoising Pretraining" objective. It was introduced in Multilingual Translation with Extensible Multilingual Pretraining and Finetuning paper. mBART-50 is a multilingual Sequence-to-Sequence model. It was introduced to show that multilingual translation models can be created through multilingual fine-tuning. Instead of fine-tuning on one direction, a pre-trained model is fine-tuned on many directions simultaneously. mBART-50 is created using the original mBART model and extended to add extra 25 languages to support multilingual machine translation models of 50 languages. The pre-training objective is explained below. **Multilingual Denoising Pretraining**: The model incorporates N languages by concatenating data: `D = {D1, ..., DN }` where each Di is a collection of monolingual documents in language `i`. The source documents are noised using two schemes, first randomly shuffling the original sentences' order, and second a novel in-filling scheme, where spans of text are replaced with a single mask token. The model is then tasked to reconstruct the original text. 35% of each instance's words are masked by random sampling a span length according to a Poisson distribution `(λ = 3.5)`. The decoder input is the original text with one position offset. A language id symbol `LID` is used as the initial token to predict the sentence.

• gemma-3-1b-pt↗

  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.

• Solon-embeddings-large-0.1↗

  OrdalieTech

  **Instructions :** Add "query : " before the *query* to retrieve to increase performance of retrieval. No instructions needed for *passages*. These results have been obtained through 9 french benchmarks on a variety of text similarity tasks (classification, reranking, STS) : - AmazonReviewsClassification (MTEB) - MassiveIntentClassification (MTEB) - MassiveScenarioClassification (MTEB) - MTOPDomainClassification (MTEB) - MTOPIntentClassification (MTEB) - STS22 (MTEB) - MiraclFRRerank (Miracl) - OrdalieFRSTS (Ordalie) - OrdalieFRReranking (Ordalie) We created OrdalieFRSTS and OrdalieFRReranking to enhance the benchmarking capabilities of French STS and reranking assessments.

• granite-3.3-2b-base↗

  ibm-granite

  Granite-3.3-2B-Base is a decoder-only language model with a 128K token context window. It improves upon Granite-3.1-2B-Base by adding support for Fill-in-the-Middle (FIM) using specialized tokens, enabling the model to generate content conditioned on both prefix and suffix. This makes it well-suited for code completion tasks. **Supported Languages:** English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 3.3 models for languages beyond these 12 languages. **Intended Use:** Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, and other long-context tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.

• kling-video-multi-elements-create↗

  快手 · 可灵

  콰이쇼 커링은 공식 인증 API를 제공하며, 안전하고 안정적입니다. 동기화 업데이트는 공식 모든 모델을 지원하며, 과금 방식도 공식과 동일합니다. 연동 시에는 공식 API 도메인과 토큰만 본사로 교체하면 됩니다.

• NSFW_Wan_14b↗

  NSFW-API

  **NSFW Wan 14B T2V** is a massive, 14 billion parameter text-to-video generation model, specifically fine-tuned for generating Not Safe For Work (NSFW) content. This model was created using a unified training methodology to build a solid understanding across the entire NSFW spectrum and generate videos with coherent motion natively. The primary goal of this model is to provide a research and creative tool capable of generating thematically relevant short video clips based on text prompts within the adult content domain. It aims to understand and render a wide array of NSFW scenarios, aesthetics, and actions described in natural language with high fidelity and temporal consistency. Unlike previous multi-phase approaches, the 14B model was trained using a single, unified configuration from the ground up to ensure maximum quality and stability from the very first epoch.

• H3-Fight-Flow-Fight-Interaction-LoRA↗

  JOKER141

  The previous action should create the starting state of the next one, instead of constantly resetting back to a neutral pose. Fight Flow V1 does not mainly teach new moves. It explores whether H3 can learn how two or more characters should actually fight together. Unlike regular LoRA training that mainly relies on captions, D-OPSD allows the Teacher to directly reference the target training video.

• ERNIE-4.5-21B-A3B-MLX-6bit↗

  lmstudio-community

  *👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** baidu **Original model**: ERNIE-4.5-21B-A3B-PT **MLX quantization:** provided by LM Studio team using mlx_lm 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.

• Hermes-2-Pro-Mistral-7B-GGUF↗

  backyardai

  *** - **Creator:** Nous Research - **Original:** Hermes 2 Pro Mistral 7B - **Date Created:** 2024-03-11 - **Trained Context:** 8192 tokens - **Description:** Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house. This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation. *** GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Backyard AI. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware. GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.