Koko210/miku-discord
1
0
Fork 0
Code Issues 34 Pull Requests Actions Packages Projects Releases Wiki Activity
120 Commits 1 Branch 0 Tags
d5b9964ce7e2148a253cea17e91b2c8751993c69
Commit Graph

7 Commits

Author SHA1 Message Date
koko210Serve
eafab336b4 feat: add Traefik proxy, custom chat template, improve Cheshire Cat memory 
docker-compose.yml:
- Add Traefik proxy network + labels for miku.panel domain
- Connect miku-bot service to proxy network

llama-swap-config.yaml / llama-swap-rocm-config.yaml:
- Add --chat-template-file flag to disable Llama 3.1 built-in tool
  calling (was causing malformed responses)
- ROCm config: add Rocinante-X 12B model entry for comparison testing

cheshire-cat discord_bridge plugin:
- Increase declarative memory recall (k=3→10, threshold 0.7→0.5)
  for better factual retrieval
- Add agent_prompt_prefix hook to enforce factual accuracy from
  declarative memories
- Add before_agent_starts debug logging for memory inspection
- Add passthrough hooks for message/suffix pipeline
 2026-03-04 00:48:58 +02:00
koko210Serve
5b1163c7af Removed KV Cache offloading to increase performance 2026-01-30 21:35:07 +02:00
koko210Serve
c0aaab0c3a Disabled KV cache offloading on llama-server and enabled Flash Attention. Performance gains in the tens. 2026-01-27 19:11:49 +02:00
koko210Serve
fe0962118b Implemented new Japanese only text mode with WebUI toggle, utilizing a llama3.1 swallow dataset model. Next up is Japanese TTS. 2026-01-23 15:02:36 +02:00
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
koko210Serve
675bb21653 Disable model warmup to improve switching speed 
- Added --no-warmup flag to both llama3.1 and vision models
- Reduces model switch time by 2-5 seconds per swap
- No impact on response quality, only minor first-token latency
- Better for frequent model switching use case and tight VRAM budget
 2025-12-10 10:09:37 +02:00
koko210Serve
8c74ad5260 Initial commit: Miku Discord Bot 2025-12-07 17:15:09 +02:00