File size: 629 Bytes
c984ba3 d7ac491 4e7126d 0afecbd |
1 2 3 4 5 |
Custom GGUF quants of [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B), where the Output Tensors are quantized to Q8_0 while the Embeddings are kept at F32. Enjoy! 🧠🔥🚀
Update: This repo now contains OF32.EF32 GGUF IQuants for even more accuracy. Enjoy! 😋
UPDATE: This repo now contains updated O.E.IQuants, which were quantized, using a new F32-imatrix, using llama.cpp version: 4658 (855cd073). This particular version of llama.cpp added support for Non-Contiguous RMS Norms. This has enhanced model coherence and further increased model creativity (from testing). |