Files
miku-discord/llama-swap-config.yaml
koko210Serve 6ec33bcecb Implement Evil Miku mode with persistence, fix API event loop issues, and improve formatting
- Added Evil Miku mode with 4 evil moods (aggressive, cunning, sarcastic, evil_neutral)
- Created evil mode content files (evil_miku_lore.txt, evil_miku_prompt.txt, evil_miku_lyrics.txt)
- Implemented persistent evil mode state across restarts (saves to memory/evil_mode_state.json)
- Fixed API endpoints to use client.loop.create_task() to prevent timeout errors
- Added evil mode toggle in web UI with red theme styling
- Modified mood rotation to handle evil mode
- Configured DarkIdol uncensored model for evil mode text generation
- Reduced system prompt redundancy by removing duplicate content
- Added markdown escape for single asterisks (actions) while preserving bold formatting
- Evil mode now persists username, pfp, and nicknames across restarts without re-applying changes
2026-01-02 17:11:58 +02:00

34 lines
1.3 KiB
YAML

# llama-swap configuration for Miku Discord Bot
# This manages automatic model switching and unloading
models:
# Main text generation model (Llama 3.1 8B)
llama3.1:
cmd: /app/llama-server --port ${PORT} --model /models/Llama-3.1-8B-Instruct-UD-Q4_K_XL.gguf -ngl 99 -nkvo -c 16384 --host 0.0.0.0 --no-warmup
ttl: 1800 # Unload after 30 minutes of inactivity (1800 seconds)
aliases:
- llama3.1
- text-model
# Evil/Uncensored text generation model (DarkIdol-Llama 3.1 8B)
darkidol:
cmd: /app/llama-server --port ${PORT} --model /models/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored_Q4_K_M.gguf -ngl 99 -nkvo -c 16384 --host 0.0.0.0 --no-warmup
ttl: 1800 # Unload after 30 minutes of inactivity
aliases:
- darkidol
- evil-model
- uncensored
# Vision/Multimodal model (MiniCPM-V-4.5 - supports images, video, and GIFs)
vision:
cmd: /app/llama-server --port ${PORT} --model /models/MiniCPM-V-4_5-Q3_K_S.gguf --mmproj /models/MiniCPM-V-4_5-mmproj-f16.gguf -ngl 99 -c 4096 --host 0.0.0.0 --no-warmup
ttl: 900 # Vision model used less frequently, shorter TTL (15 minutes = 900 seconds)
aliases:
- vision
- vision-model
- minicpm
# Server configuration
# llama-swap will listen on this address
# Inside Docker, we bind to 0.0.0.0 to allow bot container to connect