저장한 도구도구 추천
FOXAI SEARCH

전체 검색

AI 모델 2119

  • Minimax-H3-Quantfunc-4bit↗

    QuantFunc

    🌐 Website  |  🐙 GitHub  |  🤗 Hugging Face  |  🤖 ModelScope  |  🎨 Civitai  |  🎮 Discord QuantFunc INT4 cuts MiniMax H3's core weight precision from 16-bit to 4-bit. Character detail, style fidelity and fast motion stay clear and coherent, while H3's native video+audio generation is fully preserved. In our internal FL2VA evaluation, QuantFunc INT4 vs the BF16 baseline (same prompt, same seed) measures ~**23.7 dB PSNR**.

  • Janus-Pro-7B↗

    DeepSeek

    Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. Janus-Pro surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus-Pro make it a strong candidate for next-generation unified multimodal models. Janus-Pro is a unified understanding and generation MLLM, which decouples visual encoding for multimodal understanding and generation. Janus-Pro is constructed based on the DeepSeek-LLM-1.5b-base/DeepSeek-LLM-7b-base. For multimodal understanding, it uses the SigLIP-L as the vision encoder, which supports 384 x 384 image input. For image generation, Janus-Pro uses the tokenizer from here with a downsample rate of 16.

  • sam-audio-large↗

    facebook

  • distilbert-base-cased↗

    distilbert

    This model is a distilled version of the BERT base model. It was introduced in this paper. The code for the distillation process can be found here. This model is cased: it does make a difference between english and English. All the training details on the pre-training, the uses, limitations and potential biases (included below) are the same as for DistilBERT-base-uncased. We highly encourage to check it if you want to know more. DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained with three objectives:

  • Splade_PP_en_v1↗

    prithivida

    This work stands on the shoulders of 2 robust researches: Naver's From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective paper and Google's SparseEmbed. Props to both the teams for such a robust work. **Beginner ?** expand this. **Expert in Sparse & Dense representations ?** feel free skip to next section 2, Lexical search with BOW based sparse vectors are strong baselines, but they famously suffer from vocabulary mismatch problem, as they can only do exact term matching. Here are the pros and cons:

  • Nous-Hermes-Llama2-70B-GGUF↗

    TheBloke

    GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. The creator of the source model has listed its license as `['mit']`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

  • flux-3-image-klein-base-GGUF↗

    unsloth

    This is a GGUF quantized version of FLUX 3 Image Klein Base by Black Forest Labs, the 5.6B image transformer (undistilled checkpoint, 50 steps with CFG 3.5) for text to image and image editing. unsloth/flux-3-image-klein-base-GGUF uses Unsloth Dynamic 2.0 methodology: the `UD-` files are mixed precision, with every layer's type chosen from a measured sensitivity scan, and they beat the uniform files at the same size. - Loads in diffusers through `Flux3Transformer2DModel.from_single_file(..., quantization_config=GGUFQuantizationConfig(...))`. Also loads in Unsloth Desktop. - Tensor names follow the original Black Forest Labs checkpoint layout. The text encoder (Qwen3-VL-4B-Instruct) and the VAE are unchanged and identical to the distilled release; take them from black-forest-labs/flux-3-image-klein-base or black-forest-labs/flux-3-image-klein. **Recommended:** `UD-Q4_K_XL` (3.93 GB) for most GPUs: LPIPS 0.057 against 0.077 for `Q4_K_M`. `UD-Q5_K_XL` (4.48 GB) is closer to bf16 than `Q6_K`. For output closest to bf16 use `Q8_0`; on small cards use `UD-Q2_K_XL` (2.62 GB). LPIPS (alex, lower is better) and SSIM against the bf16 transformer, same prompt, seed, noise and text encoder, 50 steps at CFG 3.5, over 19 renders: 8 held-out prompts at 1024x1024 plus 11 text-to-image and editing cases (single and multi-reference). A repeated bf16 render scores 0, so the numbers measure only the quantization.

  • distilbert-base-uncased↗

    distilbert

    This model is a distilled version of the BERT base model. It was introduced in this paper. The code for the distillation process can be found here. This model is uncased: it does not make a difference between english and English. DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained with three objectives: This way, the model learns the same inner representation of the English language than its teacher model, while being faster for inference or downstream tasks.

  • sam2.1-hiera-large↗

    facebook

    Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and videos from FAIR. See the SAM 2 paper for more information. The official code is publicly release in this repo. Refer to the demo notebooks for more details.

  • kosamasi↗

    kosamasi