Fixed 3.1 GGUFs require KoboldCPP 1.17.1 or newer to run.
Original Model: https://huggingface.co./NeverSleep/Lumimaid-v0.2-8B
made with https://huggingface.co./FantasiaFoundry/GGUF-Quantization-Script
Models Q2_K_L, Q4_K_L, Q5_K_L, Q6_K_L, are using Q_8 output tensors and token embeddings
using bartowski's imatrix dataset
- Downloads last month
- 7
Model tree for Reiterate3680/Lumimaid-v0.2-8B-GGUF
Base model
NeverSleep/Lumimaid-v0.2-8B