全站搜索

AI 模型 84760

• nsfw-detection-2-nano↗

  viddexa

• CalmaCatCoder-Next-mini↗

  ViorikaAI-org

• VertaLily-1.2-1B-GGUF↗

  VLTX

• wd-1-5-beta3↗

  waifu-diffusion

• TwIL-LM↗

  webAI-Official

  A 1.7B reasoning model for **formal logic** tasks, built from `HuggingFaceTB/SmolLM2-1.7B-Instruct` through LoRA supervised fine-tuning, checkpoint fusion, WiSE-FT weight interpolation, and entropy-weighted GRPO reinforcement learning. It raises in-domain formal-logic performance by **+49% relative** over its base model (macro gate 0.263 → 0.393), and on the strict, no-partial-credit reading of Track A it is the strongest model we have measured at any size — ahead of Qwen3-8B and of a 26B Gemma-4 MoE. Its larger sibling, **TwIL-LM3** (3B, from SmolLM3), trades a smaller in-domain gain for strictly better held-out retention. If you care about not regressing on general benchmarks, prefer that one.

• WebVIA-Agent↗

  zai-org

• ZONOS2-GGUF↗

  Zyphra

  GGUF weights for **Zyphra/ZONOS2**, ready to run with **zonos2.cpp** — a standalone ggml/GGUF C++ port of ZONOS2. The **entire pipeline** (ECAPA speaker encoder → MoE backbone → DAC vocoder) runs as native C++ linking only `libggml` + `gguf`: **no Python, no PyTorch, no CUDA-only kernels at inference time.** CPU and CUDA use the same files. ZONOS2 is Zyphra's latest text-to-speech model, trained on more than 6 million hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers at low latency with MoE. ZONOS2 excels at high-fidelity and naturalistic voice cloning. **For model details and speech samples, check out our blog.** **A hosted version is available at cloud.zyphra.com/audio-playground.**

• drama-3-int4↗

  akhaliq

• TabSTAR-paper-version-fold-k1↗

  alana89

• Qwen-Image-2.1-Fun-Acc-LoRAs↗

  alibaba-pai

  We apply Parallel Decoding Distillation (PDD) 1 to Qwen-Image-2.1, enabling efficient text-to-image and instruction-based image editing at **4 NFE**. > [!NOTE] > The editing prompts and reference images are from the Qwen-Image-2.1 (flag) and Viggle's demo examples (woman and cat; person, cat and bird). Use a VideoX-Fun checkout exposing `QwenImage21Pipeline` from `videox_fun.pipeline`. These entries use that pipeline and the same bundled `qwenimage21_pdd.py` / `lora_utils_pdd.py` as the standalone entries;