전체 검색

AI 모델 85003

• Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES-GGUF↗

  TheBloke

• StableBeluga2-70B-GPTQ↗

  TheBloke

• beitv2_base_patch16_224.in1k_ft_in22k↗

  timm

  A BEiT-v2 image classification model. Trained on ImageNet-1k with self-supervised masked image modelling (MIM) using a VQ-KD encoder as a visual tokenizer (via OpenAI CLIP B/16 teacher). Fine-tuned on ImageNet-22k. - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 102.6 - GMACs: 17.6 - Activations (M): 23.9 - Image size: 224 x 224 - **Papers:** - BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers: https://arxiv.org/abs/2208.06366 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 - **Dataset:** ImageNet-22k - **Original:** https://github.com/microsoft/unilm/tree/master/beit2 Explore the dataset and runtime metrics of this model in timm model results.

• crossvit_9_dagger_240.in1k↗

  timm

• ecaresnet50t.a1_in1k↗

  timm

  This model features: * ReLU activations * tiered 3-layer stem of 3x3 convolutions with pooling * 2x2 average pool + 1x1 convolution shortcut downsample * Efficient Channel Attention Recipe details: * ResNet Strikes Back `A1` recipe * LAMB optimizer with BCE loss * Cosine LR schedule with warmup

• mobilevitv2_175.cvnets_in1k↗

  timm

• embeddinggemma-2-GGUF↗

  unsloth

  Unsloth Dynamic 3.0 achieves superior accuracy & outperforms other leading quants. **EmbeddingGemma 2** is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders. Designed to run on consumer hardware such as mobile devices and laptops, EmbeddingGemma 2 delivers low-latency semantic representations for on-device applications, like search, retrieval-augmented generation (RAG), classification, and clustering.

• Wan2.2-Animate-14B-Diffusers↗

  Wan-AI

• llama-68m↗

  Xenova

• Qwen3.6-35B-A3B-Abliterated-Heretic-GGUF↗

  Youssofal

  By applying Heretic on the Qwen 3.6 sparse-MoE text stack, the base refusal behavior was removed at the weight level. The result keeps Qwen3.6-35B-A3B's multimodal architecture and general capability profile, while no longer defaulting to the original refusal pattern. Qwen3.6-35B-A3B is a 35.95B sparse MoE vision-language model with roughly 3B active parameters per token, 40 text layers, 256 routed experts, and 8 active experts per token. This release was produced with a Heretic MPOA/SOMA-style sibling-transfer run, finalized with a split-MoE input-side intervention on the accepted candidate.