Joseph717171's picture
Update README.md
1f34f10 verified
|
raw
history blame
229 Bytes

Custom GGUF quants of arcee-ai’s Llama-3.1-SuperNova-Lite-8B, where the Output Tensors are quantized to Q8_0 while the Embeddings are kept at F32. Enjoy! 🧠🔥🚀