Solstice-AI/GLM-5.3-Flash-UNCENSORED-NVFP4-DFlash2

feat: update tokenizer_config chat_template to Solstice 10-level solo + swarm

feat: update to Solstice 10-level solo + swarm cognitive architecture

chore: remove redundant fp16 mmproj in favor of superior bf16

feat(vision): add official standalone mmproj-F16.gguf for llama.cpp vision support

feat(vision): add official standalone mmproj-BF16.gguf for llama.cpp vision support

Upload official Solstice-AI GLM-5.3-Flash-UNCENSORED W4A16 NVFP4 Model Card

Update quantization_config to official W4A16 NVFP4

Copy files from models/Anbeeld/GLM-5.3-Flash-DFlash2-GGUF

Copy files from models/Anbeeld/GLM-5.3-Flash-DFlash2-GGUF

Copy files from models/dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4

Copy files from models/dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4

initial commit