サイト内検索
AI モデル 85012
- Mr.Chatterbox-2.7B-Chat-ONNX↗
liodon-ai
- Llama-3-Smaug-8B-GGUF↗
LiteLLMs
- privacy-filter-multilingual-GGUF↗
LocalAI-io
GGUF conversion of `OpenMed/privacy-filter-multilingual`, a multilingual PII **token-classification** model (a fine-tune of `openai/privacy-filter`). It labels every token with a BIOES tag over **54 PII categories (217 classes)** across **16 languages**, so it can be served locally with **no Python** as the encoder/NER tier of a PII redactor. For the full model description, label space, evaluation, limitations, and citations, see the **source model card** — this card only covers the GGUF packaging and how to run it. This GGUF uses a **custom architecture, `openai-privacy-filter`**, that is not (yet) part of upstream llama.cpp. It runs on:
- gemma-4-E2B-meeting-agent-zh↗
Luigi
- libero4in1_wan2.2vae_latent_cosmos_style↗
MangoGoes
> ⚠️ **Mirror-only**: 数据已迁移到正确的 **dataset 类型仓库**,请优先使用: > 👉 **https://huggingface.co/datasets/MangoGoes/libero4in1_wan2.2vae_latent_dataset** > > 本仓库(`repo_type='model'`)保留作为镜像,文件内容完全一致。下载时建议从 dataset 仓库拉,可享受 dataset viewer / parquet 流式预览等特性。 LIBERO 4in1(libero_spatial / libero_object / libero_goal / libero_10)共 53.19 GB 的 Wan2.2-VAE 编码 latent 缓存:
- Peagle-9b↗
maxcurrent
Hey there! 👋 Welcome to the Peagle-14b! This is a merge of multiple models brought together using the awesome VortexMerge kit. Let's see what we've got in this merge: * mlabonne/NeuralBeagle14-7B 🚀 * eldogbbhed/NeuralPearlBeagle 🚀 ```yaml slices: - sources: - model: mlabonne/NeuralBeagle14-7B layer_range: [0, 20] - sources: - model: eldogbbhed/NeuralPearlBeagle layer_range: [12, 32] merge_method: passthrough
- zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.2-slerp-GGUF↗
MaziyarPanahi
- ACEStep-XL-Regrind-V1↗
mdmachine
**Fine-tuned VAE decoder and DiT LoRA targeting the Oobleck hum artifact series at the weight level** ACEStep XL Turbo and the Oobleck VAE produce a characteristic harmonic artifact present in all generations. The artifact has two independent origins: **VAE decoder bias** — static reconstruction bias baked into the Oobleck decoder during its original training. Present at consistent amplitude across all generations, independent of length. Characterized via Ableton EQ Eight direct measurement:
- KasbahTTS-V0↗
MenaVoice
- layoutlmv2-large-uncased↗
Microsoft
LayoutLMv2 is an improved version of LayoutLM with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. It outperforms strong baselines and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including , including FUNSD (0.7895 → 0.8420), CORD (0.9493 → 0.9601), SROIE (0.9524 → 0.9781), Kleister-NDA (0.834 → 0.852), RVL-CDIP (0.9443 → 0.9564), and DocVQA (0.7295 → 0.8672). LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou, ACL 2021
