Add quantized GGUF model (Q4_K_M, 4.1GB) - recommended

Add full precision GGUF model (F16, 14GB)

Restore comprehensive README with both usage options and YAML metadata

Add YAML metadata to model card

Update README with both LoRA and merged model usage options

Upload merged SCI Assistant model (OpenHermes-2.5-Mistral-7B + SCI LoRA)

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload adapter_config.json with huggingface_hub

Upload folder using huggingface_hub

initial commit