diffuse-cpp/Dream-v0-Instruct-7B-GGUF

docs: improve model card with quickstart, benchmarks, Apache-2.0

Remove F16 GGUF (redundant, keep Q4_K_M + Q8_0)

Upload dream-7b-q8_0.gguf with huggingface_hub

Upload dream-7b-q4km.gguf with huggingface_hub

Upload dream-7b-f16.gguf with huggingface_hub

Upload README.md with huggingface_hub

initial commit