サイト内検索

AI モデル 84759

• Winery-Qwen3.5-9B-Assemblage-GGUF↗

  WineryLabs

• Spark-X2.5-4B↗

  XHToken

  > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose language models designed to make capable AI more practical, efficient, and accessible. The models deliver strong performance across a broad range of everyday tasks—including conversation, writing, translation, reasoning, coding, tool use, and agentic workflows—achieving leading results among open-source models of comparable size. Spark-X2.5 combines an efficiency-oriented architecture with native context windows of up to 1M tokens, and support for more than 200 languages. **Technical Highlights**: - **Efficient Architecture and Native 1M-token Context**: The models use a hybrid attention architecture that combines one full-attention layer with three sliding-window attention layers. This design substantially reduces the computational overhead typically associated with long-context models while natively supporting a context window of up to 1M tokens. - **Strong Coding and Agent Capabilities**: The models are deeply integrated with popular agent harnesses, including Codex, Claude Code, OpenClaw, and Hermes. They deliver state-of-the-art performance among models of comparable size across everyday coding, agentic workflows, reasoning, and instruction-following tasks. - **Broad Hardware and Software Compatibility**: The models support a wide range of hardware platforms, including NVIDIA, Huawei, Hygon, HOUMO.AI, etc. It is compatible with leading inference frameworks such as vLLM, SGLang, llama.cpp, MLX, and can be deployed quickly through platforms including Ollama and LM Studio. The models can also be customized using popular fine-tuning frameworks such as LLaMA-Factory. Across multiple hardware platforms, they deliver superior TTFT, TOPT, and overall inference efficiency compared with similarly sized models. - **Advanced Training Algorithms**: The models were trained on Huawei Ascend clusters. Large-scale reinforcement learning and post-training techniques such as MOPD significantly enhance its reasoning, coding, agentic, and instruction-following capabilities.

• embeddinggemma-2-GGUF↗

  yan2026

• LFM2.5-1.2B-Thinking-imatrix-GGUF↗

  ZuzeTt

• seethroughv0.0.2_layerdiff3d_nf4↗

  24yearsold

  A 4-bit NF4 quantisation of layerdifforg/seethroughv0.0.2_layerdiff3d for GPUs with less memory. The UNet and both text encoders are quantised with bitsandbytes (NF4, bfloat16 compute dtype). The VAE and the transparent VAE are unquantised and identical to the full model. It is used by `inference/scripts/inference_psd_quantized.py` (the default `--quant_mode nf4`), which needs `requirements-inference-bnb.txt`. Read our GitHub repository for usage and details. The See-through code is licensed under Apache-2.0. These weights are released under Apache-2.0 for our own contributions, and they also inherit the licences of the models they are derived from:

• Minimax-H3-nvfp4-INT4-INT8-Convrot↗

  Abiray

  This repository is a community-compiled collection of quantized and pruned weights for **MiniMax H3 (Hailuo 3.0)**, optimized for local inference environments like ComfyUI. By unifying various quantization formats (INT4, INT8, Mixed, and NVFP4) into a single structured repository, this hub makes it easier for users with consumer GPUs (16GB - 24GB VRAM) to experiment with MiniMax H3's powerful omni-modal text/image/audio-to-video generation capabilities. If you are new to local generation and aren't sure what to download, use this guide based on your graphics card.

• Minimax-h3-Singularity-V2-Pruned-GGUF↗

  Abiray

• ruT5-large↗

  ai-forever

• epiCPhoto-XL-LoRA-Derp2↗

  AiWise

• Evoke-Turbo↗

  AlayaLab

  **Alaya-EVOKE-Turbo** is a **controllability-optimized** version of Alaya-EVOKE, focusing on camera-motion following and scene/subject instruction adherence. It uses the same architecture and inference workflow: **3 steps, no CFG, 384 × 640 at 24 fps**. Merged Turbo transformer weights, stored in **FP32** to match Evoke. Download the shared base components and depth backend separately: See Evoke for camera control, other inference modes, and long rollouts.