Search FoxAI

AI Models 2119

• gemma-3-270m-it-qat-GGUF↗

  unsloth

  > [!NOTE] > Please use the correct settings: `temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0` > 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, the 1B with 2 trillion tokens, and the 270M with 6 trillion tokens. The knowledge cutoff date for the training data was August 2024. Here are the key components:

• Llama3.1-Aloe-Beta-8B↗

  HPAI-BSC

  Llama3.1-Aloe-Beta-8B is an **open healthcare LLM** achieving **state-of-the-art performance** on several medical tasks. Aloe Beta is made available in four model sizes: 7B, 8B, 70B, and 72B. All models are trained using the same recipe, on top of two different families of models: Llama3.1 and Qwen2.5. Aloe is trained on 20 medical tasks, resulting in a robust and versatile healthcare model. Evaluations show Aloe models to be among the best in their class. When combined with a RAG system (also released) the 7B and 8B version gets close to the performance of closed models like MedPalm-2, GPT4. With the same RAG system, Llama3.1-Aloe-Beta-70B and Qwen2.5-Aloe-Beta-72B outperforms those private alternatives, producing state-of-the-art results. **Aloe-8B-Beta** is the latest iteration in the **Aloe family**, building and improving on the success of its predecessor, Aloe-8B-Alpha. Beta more than triples the training data used by Alpha, for a total of **1.8B tokens**, including a wider variety of medical tasks and instructions (e.g., text summarization, explanation, diagnosis, text classification, treatment recommendation, ...).

• Gf_style2↗

  xiaolxl

  欢迎使用Gf_style2模型 - 这是一个中国华丽古风风格模型，也可以说是一个古风游戏角色模型，具有2.5D的质感。第二代相对与第一代减少了上手难度，不需要固定的配置也能生成好看的图片。同时也改进了上一代脸崩坏的问题。 Welcome to Gf_ Style2 model - This is a Chinese gorgeous antique style model, which can also be said to be an antique game role model with a 2.5D texture. Compared with the first generation, the second generation reduces the difficulty of getting started and can generate beautiful pictures without fixed configuration. At the same time, it also improved the problem of face collapse of the previous generation. 2. 模型自带VAE如果你的程序无法加载请记住选择任意一个VAE文件，否则图形将为灰色 - The model comes with VAE. If your program cannot be loaded, please remember to select any VAE file, otherwise the drawing will be gray

• bert_uncased_L-2_H-256_A-4↗

  Google

  This is the set of 24 BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.

• SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nex↗

  lmsys

  **SpecBundle** is an open-source initiative, jointly driven by the community and industry, to democratize speculative decoding by providing high-performance speculative decoding draft weights for mainstream open-source models. This checkpoint was trained by the **Nex-AGI** Team and released as the **phase 1 of SpecBundle release**. We regenerated the responses in the mlabonne/open-perfectblend and trained the model on 1.4M data samples for 2 epochs. This checkpoint was trained using the **SpecForge** framework. We sincerely appreciate the collective efforts from both the developers in the open-source community and our industrial partners, especially Ant Group AQ Team, Meituan, Nex-AGI (Qiji Zhifeng), EigenAI for their invaluable contributions to the release of SpecBundle Phase 1.

• MiniMax-M1-40k↗

  MiniMaxAI

  We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters activated per token. Consistent with MiniMax-Text-01, the M1 model natively supports a context length of 1 million tokens, 8x the context size of DeepSeek R1. Furthermore, the lightning attention mechanism in MiniMax-M1 enables efficient scaling of test-time compute – For example, compared to DeepSeek R1, M1 consumes 25% of the FLOPs at a generation length of 100K tokens. These properties make M1 particularly suitable for complex tasks that require processing long inputs and thinking extensively. MiniMax-M1 is trained using large-scale reinforcement learning (RL) on diverse problems ranging from traditional mathematical reasoning to sandbox-based, real-world software engineering environments. We develop an efficient RL scaling framework for M1 highlighting two perspectives: (1) We propose CISPO, a novel algorithm that clips importance sampling weights instead of token updates, which outperforms other competitive RL variants; (2) Our hybrid-attention design naturally enhances the efficiency of RL, where we address unique challenges when scaling RL with the hybrid architecture. We train two versions of MiniMax-M1 models with 40K and 80K thinking budgets respectively. Experiments on standard benchmarks show that our models outperform other strong open-weight models such as the original DeepSeek-R1 and Qwen3-235B, particularly on complex software engineering, tool using, and long context tasks. With efficient scaling of test-time compute, MiniMax-M1 serves as a strong foundation for next-generation language model agents to reason and tackle real-world challenges. Benchmark performance comparison of leading commercial and open-weight models across competition-level mathematics, coding, software engineering, agentic tool use, and long-context understanding tasks. We use the MiniMax-M1-80k model here for MiniMax-M1. We report results derived from the Agentless scaffold. Departing from the original pipeline, our methodology employs a two-stage localization process (without any embedding-based retrieval mec

• sam-audio-large↗

  mrfakename

• sdxl-turbo↗

  Nextcloud-AI

  SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. A real-time demo is available here: http://clipdrop.co/stable-diffusion-turbo SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis. SDXL-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. This approach uses score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal and combines this with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps. For research purposes, we recommend our `generative-models` Github repository (https://github.com/Stability-AI/generative-models), which implements the most popular diffusion frameworks (both training and inference).

• xtts-v2-yoruba-openbible-conversational↗

  samuelolubukun

• Nous-Puffin-70B-GGUF↗

  TheBloke

  GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. The creator of the source model has listed its license as `['mit']`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.