Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

AI Models 2119

  • sam2.1-hiera-small-ONNX↗

    onnx-community

  • chandohasam↗

    samvaran

  • Qwen3.8-27B-Uncensored-NVFP4-NInferV3↗

    wallawalla47

    **A single-file NInfer V3 (`.ninfer`) artifact of orcarouter/Qwen3.8-27B-Uncensored-NVFP4, built for an NVIDIA RTX 5090 (sm_120a), for Infernix (recommended) and NInfer. No conversion step at load time: point `infernix-serve` (or `ninfer-serve`) at the `.ninfer` file and run.** This repository is the NInfer form of the orcarouter checkpoint above, an abliterated (refusal-removed) mixed NVFP4/FP8 build of Qwen3.8-27B. Its NVFP4 and FP8 weights are carried over **bit-exactly** for every transformer linear, and two speculative-decoding components (DFlash2 draft model, indexed proposal head) are added so the artifact runs with the engines' fastest decode paths. **Recommended engine: Infernix**, my engine grown from NInfer, which replaces my earlier ninfer-custom fork. In an agentic coding replay on the 27B it served 90 % of prompt tokens from its prefix cache and reached the first token in about half NInfer's average time, and it prefills long prompts 1.3-1.5× faster, at the same quality (benchmarks, measured on NInfer's official 27B artifact). It also runs Qwen3.8-Flash-Next. The artifact still works with NInfer itself and with ninfer-custom.

  • SONAR_200_text_encoder↗

    cointegrated

    This is a port of the multilingual SONAR text encoder (https://huggingface.co/facebook/SONAR) to the `transformers` format from `fairseq2`. Its embeddings are expected be equal to those the official implementation (https://github.com/facebookresearch/SONAR), but the latter stays the source of truth. The encoder supports the same 202 languages as NLLB-200 (see also the source model card and FLORES-200 lang code mapping).

  • Qwen2.5-0.5B-Instruct-int4-sym-inc↗

    OPEA

    This model is an int4 model with group_size 128 and symmetric quantization of Qwen/Qwen2.5-0.5B-Instruct generated by intel/auto-round. Load the model with `revision="7cac2d1"` to use AutoGPTQ format ⚠️ Important: This model is used for internal testing with VLLM. Please do not delete or modify without approval. Here is the sample command to generate the model. We observed a larger accuracy drop in Chinese tasks and recommend using a high-quality Chinese dataset for calibration or smaller group_size like 32.

  • dfine-nano-coco↗

    ustc-community

    The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global Optimal Localization Self-Distillation (GO-LSD). D-FINE is trained on COCO (Lin et al. [2014]) train2017 and validated on COCO val2017 dataset. We report the standard AP metrics (averaged over uniformly sampled IoU thresholds ranging from 0.50 − 0.95 with a step size of 0.05), and APval5000 commonly used in real scenarios.

  • bigaspv2-5↗

    fancyfeast

    Drag this image into ComfyUI to load the example workflow. I've done limited testing so far on running the model, so take that workflow and the following advice with a grain of salt. bigASP V2.5 is an intermediary experiment I wanted to run while I prepared for V3. Like V2, it is a large scale finetune from SDXL, and follows most of V2's approach except for these bizarre tweaks: 1. Dataset expanded from 6.7M to 13M images by including additional sources as well as, significantly, anime. Why? Because I wanted to see if the model could dual purpose for both photoreal gens and anime gens. Also I wanted to see if photoreal gens could benefit from the more varied concepts present in anime/furry/etc images. 2. Training length expanded from 40M samples to 150M samples. One of my theories for the tempermental behavior of V2 is the scale of the training. Models like Pony v6 had a much larger amount of training. 150M samples brings V2.5 within the ballpark of that class of model. 3. Using JoyCaption Beta One instead of the Pre-Alphas used in V2. Beta One has more modes, and I tweaked its language and verbage quite a bit, so hopefully V2.5 is less sensitive to prompts. 4. Swapping SDXL's training objective over to Rectified Flow Matching like more modern models (i.e. Flux, Chroma, etc). This was done for two reasons. One, Flow Matching makes higher quality generations. And two, it allowed me to ditch SDXL's broken noise schedule. That latter bit greatly enhances the model's ability to control the overall structure of generations, resulting in less mangled mess generations and extra limbs. It also allows V2.5 to generate more dynamic range from very dark images to very bright images.

  • stable-diffusion-v1-5-GGUF↗

    gpustack

    **Model creator**: Runway ML **Original model**: stable-diffusion-v1-5 **GGUF quantization**: based on stable-diffusion.cpp ac54e that patched by llama-box. Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion blog. The **Stable-Diffusion-v1-5** checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling.

  • samid-drone-detector↗

    Rashidbm

  • roberta-base-go_emotions-onnx↗

    SamLowe

    See more details in the SamLowe/roberta-base-go_emotions model card for the increases possible through selecting label-specific thresholds to maximise F1 scores, or another metric. See more details in the SamLowe/roberta-base-go_emotions model card for the increases possible through selecting label-specific thresholds to maximise F1 scores, or another metric. Optimum library has equivalents (starting `ORT`) for the main Transformers classes, so these models can be used with the familiar constructs. The only extra property needed is `file_name` on the model creation, which in the below example specifies the quantized (INT8) model.