전체 검색
AI 모델 2119
- resnet50.ram_in1k↗
timm
This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Recipe details: * AugMix (with RandAugment) recipe * SGD (w/ Nesterov) optimizer and JSD (Jensen–Shannon divergence) loss * Cosine LR schedule with warmup
- Qwen3.8-27B-RANA-abliterated-GGUF↗
abliterant
Abliterant GGUF quantizations of **abliterant/Qwen3.8-27B-RANA-abliterated**, a refusal-ablated **Qwen/Qwen3.8-27B**, for llama.cpp and compatible apps. Vision (`mmproj-*`) and the MTP speculative-decoding head (`mtp-*`) are included as separate files, in the same layout as ggml-org/Qwen3.8-27B-GGUF. Try RANA in Abliterant Chat · abliterant.ai · Research notes · All formats > **This is a safety-alignment-removed research model.** Read Intended use and > Limitations before using it. Method, full evaluation and release gates are on the > BF16 card.
- sam-3d-body↗
Blendcap
- umt5-small↗
Google
UMT5 is pretrained on the an updated version of mC4 corpus, covering 107 languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Sotho, Spanish, Sundanese, Swahili, Swedish, Tajik, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, West Frisian, Xhosa, Yiddish, Yoruba, Zulu. **Note**: UMT5 was only pre-trained on mC4 excluding any supervised training. Therefore, this model has to be fine-tuned before it is useable on a downstream task.
- whisper-medium.en-gguf↗
handy-computer
Ported from upstream commit 2e98eb6, pinned 2026-04-25. Validated against the transformers reference at transcribe.cpp commit 0a26478 on 2026-09-13. OpenAI Whisper medium.en — converted to GGUF for transcribe.cpp. English-only; faster than the multilingual model at the same size. Encoder-decoder transformer; 30-second windows with chunked long-form decoding. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.
- wav2vec2-large-xlsr-indonesian↗
indonesian-nlp
This is the model for Wav2Vec2-Large-XLSR-Indonesian, a fine-tuned facebook/wav2vec2-large-xlsr-53 model on the Indonesian Common Voice dataset. When using this model, make sure that your speech input is sampled at 16kHz. The model can be evaluated as follows on the Indonesian test data of Common Voice. The Common Voice `train`, `validation`, and synthetic voice datasets were used for training.
- Qwen3.8-27B-Huihui-Abliterated-NInfer-NVFP4↗
lyf
A complete NInfer artifact derived from huihui-ai/Huihui-Qwen3.8-27B-abliterated revision `d42ca8978c5a66e92c3446d46e8adfe03ef692ff`. The artifact combines NInfer's fixed **FP8 + NVFP4** Qwen3.8 allocation with same-source Huihui BF16 norms, embeddings, vision tower, and MTP tensors. No official Qwen or unrelated behavioral checkpoint supplies model weights. The v3 file preserves all 1,118 original tensor encodings and the entire original payload byte-for-byte. It appends the maintained Qwen3.8 chat template and adds the v3 directory and bindings. This is a container/template update, not a new quantization. It does not add an indexed proposal head or DFlash2 weights; omit `--lm-head-draft` and `--spec dflash2`.
- resnet50.a1_in1k↗
timm
This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Recipe details: * ResNet Strikes Back `A1` recipe * LAMB optimizer with BCE loss * Cosine LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 25.6 - GMACs: 4.1 - Activations (M): 11.1 - Image size: train = 224 x 224, test = 288 x 288 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - **Original:** https://github.com/huggingface/pytorch-image-models
- FastH3-Omni-NVFP4-QAD-Comfy↗
FastVideo
The ComfyUI-native NVFP4 QAD diffusion model for FastH3 Omni. It generates video with synchronized 32-kHz stereo audio from a prompt and ordered image, video and audio references in eight sampling steps. Download a compatible text encoder, video VAE and audio VAE from FastH3 Omni Comfy and place them in `ComfyUI/models/text_encoders/` and `ComfyUI/models/vae/`. The audio VAE and the text encoder's reference-vision support are required. Select a text-encoder format supported by your GPU. Accelerated NVFP4 inference requires NVIDIA Blackwell hardware. Use BF16 or FP8 on other GPU families. Quantized output can differ from BF16. This is the ComfyUI format; use the separate FastVideo-format model for FastVideo inference.
- Nemotron-3-Embed-1B-NVFP4↗
NVIDIA
**Nemotron-3-Embed-1B-NVFP4** is the quantized version of the Nemotron-3-Embed-1B-BF16 model, which is developed for text question-answering retrieval. For more information, please check here. The **Nemotron-3-Embed-1B-NVFP4** model is quantized with NVIDIA Model Optimizer, using nvidia-modelopt v0.45.0. This model was evaluated on 34 languages: English, Arabic, Assamese, Bengali, Bulgarian, Chinese, Danish, Dutch, Finnish, French, German, Hindi, Hinglish, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Nepali, Norwegian, Persian, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Ukrainian, Urdu, Vietnamese. Read more details in our Blog Post. This model and its associated configuration files are licensed under the OpenMDW License Agreement, version 1.1 (OpenMDW-1.1). ADDITIONAL INFORMATION: Apache License, Version 2.0.