全站搜索
AI 模型 2119
- Juggernaut-XL-Lightning↗
RunDiffusion
> Juggernaut XL Lightning is the **speed-optimized** member of the Juggernaut family — built on **SDXL Lightning** distillation, it produces photo-grade Juggernaut output in just **5–7 inference steps** instead of the usual 30–40. Same aesthetic, ~5× faster, ideal for batch generation, real-time iteration, and live demos. - ⚡ **Batch generation** — render hundreds of variations in the time you'd usually generate a few. - 🔁 **Real-time iteration** — preview prompt changes in seconds, not minutes. - 💻 **Lower-end hardware** — fewer steps means lower VRAM pressure during inference. - 🎤 **Live demos and showcases** — instant turnaround when latency is the bottleneck. If you need the very best per-image quality and don't mind the wait, use **Juggernaut XL v9** instead — full-step inference holds slightly more detail.
- wav2vec2-large-xlsr-53-breton↗
Marxav
The above code leads to the following prediction for the first two samples: * Prediction: ["neller ket dont a-benn eus netra la vez ser merc'hed evel sich", 'an eil hag egile'] * Reference: ["N'haller ket dont a-benn eus netra pa vezer nec'het evel-se.", 'An eil hag egile.'] The model can be evaluated as follows on the {language} test data of Common Voice. **Test Result**: 43.43% The Common Voice `train`, `validation` datasets were used for training.
- bert_uncased_L-2_H-128_A-2↗
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.
- wav2vec2-large-xlsr-53-portuguese↗
jonatasgrosman
使用 Common Voice 6.1 的训练集和验证集，在葡萄牙语上对 facebook/wav2vec2-large-xlsr-53 进行了微调。使用该模型时，请确保您的语音输入采样率为 16kHz。
- DocumentFigureClassifier-v2.5↗
docling-project
This is an image classification model based on **Google EfficientNet-B0**, fine-tuned on a subset of the subset of HuggingFace/finepdfs to classify document figures into one of the following 26 categories: 1. **logo** 2. **photograph** 3. **icon** 4. **engineering_drawing** 5. **line_chart** 6. **bar_chart** 7. **other** 8. **table** 9. **flow_chart** 10. **screenshot_from_computer** 11. **signature** 12. **screenshot_from_manual** 13. **geographical_map** 14. **pie_chart** 15. **page_thumbnail** 16. **stamp** 17. **music** 18. **calendar** 19. **qr_code** 20. **bar_code** 21. **full_page_image** 22. **scatter_plot** 23. **chemistry_structure** 24. **topographical_map** 25. **crossword_puzzle** 26. **box_plot** **Note:** This model uses the same architecture and implementation as v2.0. The improved performance is achieved by training on a dataset that is 10 times larger than the one used for v2.0.
- Qwen3.8-Flash-Next-Q8_0-Strata↗
Maximilian228
Qwen's original Qwen3.8-Flash-Next with **every routed expert in Q8_0**, rounded from the BF16 checkpoint, packed for Strata NVFP4. It is the fork's accuracy reference: the other models' accuracy below is measured against it. It needs a PC with **128 GB of RAM**, and it decodes at about a quarter of the NVFP4 GPTQ model's speed. **Quick start (Windows):** from the Strata NVFP4 release 0.1.42-nvfp4.2 or newer, run `START-HERE.bat --family qwen-q8`: it checks the PC, downloads this repository (only its experts if `qwen-nvfp4-gptq` is installed: the other files are the same) and starts the model. Strata NVFP4 0.1.42-nvfp4.1 on an RTX 5090 (32 GB), Ryzen 9 9950X3D, 128 GB of DDR5-5600, the arguments under Run it.
- Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF↗
IsValorum
**Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket.** If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. > > *Independently computed on private cloud clusters. If this handcrafted release saves you VRAM and runs faster on your GPU, consider fueling the community compute fund on Ko-fi.* > > Explore the new canonical V3 releases. MiniPlus prioritizes Q5-class to near-Q6 fidelity without a fixed file-size ceiling; NanoPlus targets Q4-class quality at a practical footprint. > > - **Qwen3.8 27B — MiniPlus V3** — 14.16 GB **(+13.21% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Qwen3.8 27B — NanoPlus V3** — 11.35 GB **(+11.49% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — MiniPlus V3** — 14.28 GB **(+5.70% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — NanoPlus V3** — 11.08 GB **(+2.26% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > > Percentages compare the reported WikiText-2 PPL with GSQ-RCO IQ3_S (7.07). The linked 27B cards document the evaluation protocol and model variants. > > **Explore the APEX-I MiniPlus V2.1 Abliterated collection** > > ### EXPLORE THE ESTABLISHED 35B MoE MINIPLUS LINEUP > These are complementary APEX-I-MiniPlus V2.1 releases, not alternate downloads of the same model. Each receives the same tensor-by-tensor approach, integrated MTP where supported, and a design suitable for full or partial system-RAM inference. Choose the model whose native strengths best fit the work you want to do: > > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1** — a versatile frontier MoE for broad reasoning, multilingual work, agents, tool use, and multimodal tasks. > - **Best for:** General reasoning, agent workflows, tool calling, and flexible multimodal use. > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1 Abliterated** — the V2.1 refusal-ablated Qwen3.6 edition for users who deliberately prefer reduced refusal behavior. > - **Best for:** Workflows where an abliterated Qwen3.6 variant is explicitly desired. > - **Ornith 1.5 APEX-I-MiniPlus-V2.1** — a software-engineering-focused MoE designed for repository-scale coding and auton
- SambaLingo-Turkish-Base-i1-GGUF↗
mradermacher
- chandra-ocr-2-FP8-dynamic↗
dangvansam
- GLM-4.7-Flash-NVFP4↗
GadflyII
This is a **mixed precision NVFP4 quantization** of zai-org/GLM-4.7-Flash, a 30B-A3B (30B total, 3B active) Mixture-of-Experts model. This model was made via custom quantization and calibration (128 samples, 2048 max seq len, neuralmagic/calibration, all 64 experts) scripts based on NVIDIA's approach for DeepSeek-V3. It uses **mixed precision** to preserve accuracy: