Javedalam/llamacpp-tiny

Switch to TinyLlama 1.1B Chat (llama.cpp-supported)

Switch to LiquidAI LFM2-350M Q4_K_M GGUF

Bake model at build; keep llama-server ENTRYPOINT

Runtime fallback: ensure /models/model.gguf exists, then exec llama-server

Use prebuilt image; ADD tiny GGUF; pass args only

Fix CMD: pass args only (ENTRYPOINT is llama-server)

Fix Dockerfile (use $MODEL_URL) and README front-matter

Add Dockerfile and README config for Hugging Face Space

Add Dockerfile for llama.cpp Space and update README

initial commit