diff --git a/gallery/index.yaml b/gallery/index.yaml index 7388eb7e0580..bc20e11510c6 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -22169,3 +22169,30 @@ - filename: Zirel-2.i1-Q4_K_S.gguf sha256: 9856e987f5f59c874a8fe26ffb2a2c5b7c60b85186131048536b3f1d91a235a6 uri: huggingface://mradermacher/Zirel-2-i1-GGUF/Zirel-2.i1-Q4_K_S.gguf +- !!merge <<: *llama3 + name: "ling-1t" + urls: + - https://huggingface.co/ubergarm2/Ling-1T-GGUF + description: | + **Ling-1T** is a 1-trillion-parameter, non-thinking flagship model from the Ling 2.0 series, designed for efficient, scalable reasoning at massive scale. Built with a **1/32 MoE (Mixture of Experts)** architecture, it activates ~50 billion parameters per token, enabling high-performance reasoning with optimized resource usage. + + Trained on **20+ trillion high-quality, reasoning-dense tokens**, Ling-1T supports up to **128K context length** and leverages **Evo-CoT (Evolutionary Chain-of-Thought)** for progressive reasoning enhancement. It achieves **state-of-the-art performance** on complex benchmarks—including math, code generation, and logical reasoning—surpassing many closed-source models in accuracy and efficiency. + + Key features: + - **FP8 mixed-precision training** for improved speed and memory efficiency + - **QK Normalization** and **aux-loss-free expert routing** for stable, scalable training + - **Syntax–Function–Aesthetics** reward system for high-quality front-end code and visual generation + - Strong performance on **AIME 25**, **BFCL V3**, and **ArtifactsBench**, ranking first among open-source models + + Ideal for advanced reasoning, code synthesis, and multi-domain tasks, Ling-1T sets a new standard for open-source, efficient large language models. + + > 📌 **Model Repository**: [huggingface.co/inclusionAI/Ling-1T](https://huggingface.co/inclusionAI/Ling-1T) + > 🚀 **Try Online**: [ZenMux](https://zenmux.ai/inclusionai/ling-1t) + > 🔗 **License**: MIT + overrides: + parameters: + model: IQ2_K + files: + - filename: IQ2_K + sha256: 77fda7661a2d3c8ab91f3d41c66ae15d8c621f08 + uri: huggingface://ubergarm2/Ling-1T-GGUF/IQ2_K