Views
No views yet
./llama.cpp/llama-cli -hf doncoriolan/sec-summarizer-gemma3-gguf --jinja./llama.cpp/llama-mtmd-cli -hf doncoriolan/sec-summarizer-gemma3-gguf --jinjagemma-3-4b-it.Q8_0.ggufgemma-3-4b-it.BF16-mmproj.ggufModelfile in the same directory as the finetuned bf16 merged modelollama create model_name -f ./Modelfile
(Replace model_name with your desired name)