Modelpublic

Joseph717171/DeepHermes-3-Mistral-24B-Preview-OQ8_0-F32.EQ8_0-F32.IQ4_K-Q8_0-GGUF

sourceHugging Faceupdated 2y agoView on Hugging Face

1likes425downloads

Model Card

Custom GGUF quants of NousResearch/DeepHermes-3-Mistral-24B-Preview, where the Output Tensors are kept at F32 or quantized to Q80, and the Embeddings are kept at F32 or Quantized to Q80. Enjoy! 🧠🔥🚀