Search FoxAI

AI Models 84759

• llama-2-13B-chat-limarp-v2-merged-GGUF↗

  TheBloke

• Llama-2-7B-fp16↗

  TheBloke

• MetaMath-Cybertron-Starling-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. These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

• thewhisper-large-v3-turbo↗

  TheStageAI

• convnext_base.clip_laiona_320↗

  timm

• densenet201.tv_in1k↗

  timm

  A DenseNet image classification model. Trained on ImageNet-1k (original torchvision weights). - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 20.0 - GMACs: 4.3 - Activations (M): 7.9 - Image size: 224 x 224 - **Papers:** - Densely Connected Convolutional Networks: https://arxiv.org/abs/1608.06993 - **Dataset:** ImageNet-1k - **Original:** https://github.com/pytorch/vision

• DeepSeek-Prover-V2-671B-GGUF↗

  unsloth

• Qwen3-235B-A22B-Thinking-2507-GGUF↗

  unsloth

  Over the past three months, we have continued to scale the **thinking capability** of Qwen3-235B-A22B, improving both the **quality and depth** of reasoning. We are pleased to introduce **Qwen3-235B-A22B-Thinking-2507**, featuring the following key enhancements: - **Significantly improved performance** on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise — achieving **state-of-the-art results among open-source thinking models**. - **Markedly better general capabilities**, such as instruction following, tool usage, text generation, and alignment with human preferences. - **Enhanced 256K long-context understanding** capabilities. **NOTE**: This version has an increased thinking length. We strongly recommend its use in highly complex reasoning tasks. **Qwen3-235B-A22B-Thinking-2507** has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 235B in total and 22B activated - Number of Paramaters (Non-Embedding): 234B - Number of Layers: 94 - Number of Attention Heads (GQA): 64 for Q and 4 for KV - Number of Experts: 128 - Number of Activated Experts: 8 - Context Length: **262,144 natively**.

• SOLAR-0-70b-16bit↗

  upstage

  Solar, a new bot created by Upstage, is now available on **Poe**. As a top-ranked model on the HuggingFace Open LLM leaderboard, and a fine tune of Llama 2, Solar is a great example of the progress enabled by open source. Try now at https://poe.com/Solar-0-70b

• Qwen3.8-Flash-Next-Splash-GGUF↗

  Vardaan97