tokinasin/llm-jp-4-vl-9b-GGUF-v0.1

Update README.md

Drop the generation-prompt fallback from the llama.cpp patch (no longer needed with the updated chat template)

Update GGUFs (loop.last chat template), mmproj (preproc_token_budget KV) and llama.cpp patch

Create README.md

Add llm-jp-4-vl-9b GGUF (BF16/Q8_0/Q6_K/Q4_K_M), mmproj, llama.cpp patch

initial commit