全站搜索
AI 模型 85003
- Gureum_1.0_neo↗
Team-CorerepubliX
- Clover3-17B-GGUF↗
TheBloke
- fin-llama-33B-GGUF↗
TheBloke
- Orca-2-7B-GGUF↗
TheBloke
- vit_base_patch16_clip_384.openai_ft_in1k↗
timm
- vit_small_patch16_dinov3.lvd1689m↗
timm
A DINOv3 ViT model image feature encoder. Distilled on LVD-1689M from the DINOv3 ViT-7B model. * The original model weights ended up with all QKV projection biases being zeroes. For `timm`, have disabled the QKV bias (`qkv_bias=False`) for the models and not loaded the zero weights. For some model sizes there are variants with `qkvb` in the name that have the bias enabled (`qkv_bias=True`), but zero, to match the behaviour of `transformers` and original models. * The original models keep RoPE periods as a persistent `bfloat16` buffer. `timm` generates `float32` periods at init. This results in some numerical differences, however the `timm` approach should be less problematic running on devices without bfloat16 support, and appears to work as well if not slightly better for fine-tuning. `model.rope.periods = model.rope.periods.to(torch.bfloat16).to(torch.float32)` will truncate the periods to bfloat16 and result in matching outputs. - **Model Type:** Image Feature Encoder - **Model Stats:** - Params (M): 21.6 - GMACs: 6.3 - Activations (M): 17.0 - Image size: 256 x 256 - **Original:** https://github.com/facebookresearch/dinov3 - **License:** DINOv3 - **Dataset:** LVD-1689M - **Papers:** - DINOv3: https://arxiv.org/abs/2508.10104 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 - PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
- Cydonia-24B-v4.3-heretic-v4-Q4-MLX↗
tstepspam
- Qwen3.5-122B-A10B-NVFP4↗
txn545
- Ministral-3-3B-Reasoning-2512-GGUF↗
unsloth
This model is the reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related use cases. The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized. Ministral 3 3B consists of two main architectural components: - **3.4B Language Model** - **0.4B Vision Encoder**
- FastVideo-FastH3-8-Step-V2-ComfyUI-GGUF↗
vantagewithai
The FastH3 8-Step V2 checkpoint from FastVideo. It generates synchronized video and audio from text with eight transformer forwards. This step-1300 model was trained with data-free DMD2 and VSA-H3 at 80% sparsity. > This checkpoint requires FastVideo's VSA-H3 attention backend. Its video > scheduler shift is 10, not the base model's 12. > This checkpoint supports text-to-audio-video generation. FL2VA and Ref2VA were not distilled. Difficult motion, fine detail, and some audio may remain below the base MiniMax H3 model. This checkpoint inherits the MiniMax H3 Community License.