全站搜索

AI 模型 84759

• mobilenetv3_large_100.ra4_e3600_r224_in1k↗

  timm

  Trained with `timm` scripts using hyper-parameters inspired by the MobileNet-V4 small, mixed with go-to hparams from `timm` and "ResNet Strikes Back". A collection of hparams (timm .yaml config files) for this training series can be found here: https://gist.github.com/rwightman/f6705cb65c03daeebca8aa129b1b94ad

• mobilenetv3_rw.rmsp_in1k↗

  timm

• Lumina-Image-2.0↗

  unsloth

• NVIDIA-Nemotron-3-Nano-4B-BF16-i1-GGUF↗

  VAREQON

• 5GHagCGfeLubZsVRVWTjys216dgszre1M4etHJ57tSYnKpsG_vgg↗

  ven1228

• all-MiniLM-L6-v2↗

  Xenova

  使用 ONNX 权重的 https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 以兼容 Transformers.js。注意：为 ONNX 权重设立单独的仓库旨在作为临时解决方案，直至 WebML 获得更多关注。如果您希望使模型适用于 Web，我们建议使用 🤗 Optimum 转换为 ONNX，并按照此仓库的结构组织您的代码库（将 ONNX 权重放置在名为 `onnx` 的子文件夹中）。

• MiMo-V2.5-Pro-FP4-DFlash↗

  XiaomiMiMo

• Qwen3-4B-RPG-Roleplay-V2↗

  Zlatiik

• Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tall_tame_panther↗

  0xgr3y

  Our pick an **experimental (advanced) mode** at this model a continuously trained `Qwen2.5-Coder-0.5B-Instruct` fine-tuned using **Gensyn RL-Swarm** framework with **GRPO (Group Relative Policy Optimization)** and supported format **GGUF (llama.cpp)** for enhanced code generation capabilities. **Note: Current training focuses on programming challenges with adaptive weighted sampling**. **Total Dataset Size:** Streaming datasets with infinite iteration **Training Samples per Round:** 2 **Evaluation:** Real-time via Swarm Coordination with Ollama-based evaluator else Judge > "When the solvers perform well, the proposer automatically increases the difficulty to keep challenging solvers to get better over time." - CodeZero-blog

• GLM-4.7-Flash-Name-NSFW-GGUF↗

  2048lr