minicpm5-1b-vivamais-v1-GGUF

GGUF export of marinarosa/minicpm5-1b-vivamais-v1 for llama.cpp-compatible local inference.

• Quantization: Q4_K_M
• Model file: minicpm5-1b-vivamais-v1-Q4_K_M.gguf
• Target use: Viva Mais dashboard Q&A in Brazilian Portuguese

This repo contains only the redacted fine-tuned model export. Raw WhatsApp exports, full transcriptions, and client identifiers are not published.

llama.cpp

Use a recent llama.cpp build with MiniCPM5 support:

cat > prompt.txt <<'EOF'
<|im_start|>system
Voce responde perguntas do painel Viva Mais usando apenas o contexto fornecido.
<|im_end|>
<|im_start|>user
Pergunta aqui
<|im_end|>
<|im_start|>assistant
EOF

llama-cli -m minicpm5-1b-vivamais-v1-Q4_K_M.gguf -c 4096 -ngl 99 -f prompt.txt

For app parity, render chat prompts with the MiniCPM5 chat template and enable_thinking=False.