3de3c8cb36
- matrix-gateway: POST /internal/matrix/presence/online endpoint - usePresenceHeartbeat hook with activity tracking - Auto away after 5 min inactivity - Offline on page close/visibility change - Integrated in MatrixChatRoom component
91 lines
3.0 KiB
YAML
91 lines
3.0 KiB
YAML
# Swapper Configuration for Node #2 (Development Node)
|
||
# Single-active LLM scheduler
|
||
# MacBook Pro M4 Max - Apple Silicon (40-core GPU, 64GB RAM)
|
||
# Auto-generated configuration with available Ollama models
|
||
|
||
swapper:
|
||
mode: single-active
|
||
max_concurrent_models: 1
|
||
model_swap_timeout: 300
|
||
gpu_enabled: true
|
||
metal_acceleration: true # Apple Silicon GPU acceleration
|
||
# Модель для автоматичного завантаження при старті (опціонально)
|
||
# Якщо не вказано - моделі завантажуються тільки за запитом
|
||
# Рекомендовано: gpt-oss:latest (швидка модель) або phi3:latest (легка модель)
|
||
default_model: gpt-oss:latest # Модель активується автоматично при старті
|
||
|
||
models:
|
||
# Fast LLM - GPT-OSS 20B (High Priority) - Main model for general tasks
|
||
gpt-oss-latest:
|
||
path: ollama:gpt-oss:latest
|
||
type: llm
|
||
size_gb: 13.0
|
||
priority: high
|
||
description: "Fast LLM for general tasks and conversations (20.9B params)"
|
||
|
||
# Lightweight LLM - Phi3 3.8B (High Priority) - Fast responses
|
||
phi3-latest:
|
||
path: ollama:phi3:latest
|
||
type: llm
|
||
size_gb: 2.2
|
||
priority: high
|
||
description: "Lightweight LLM for fast responses (3.8B params)"
|
||
|
||
# Code Specialist - StarCoder2 3B (Medium Priority) - Code engineering
|
||
starcoder2-3b:
|
||
path: ollama:starcoder2:3b
|
||
type: code
|
||
size_gb: 1.7
|
||
priority: medium
|
||
description: "Code specialist model for code engineering (3B params)"
|
||
|
||
# Reasoning Model - Mistral Nemo 12.2B (High Priority) - Advanced reasoning
|
||
mistral-nemo-12b:
|
||
path: ollama:mistral-nemo:12b
|
||
type: llm
|
||
size_gb: 7.1
|
||
priority: high
|
||
description: "Advanced reasoning model for complex tasks (12.2B params)"
|
||
|
||
# Reasoning Model - Gemma2 27B (Medium Priority) - Strategic reasoning
|
||
gemma2-27b:
|
||
path: ollama:gemma2:27b
|
||
type: llm
|
||
size_gb: 15.0
|
||
priority: medium
|
||
description: "Reasoning model for strategic tasks (27.2B params)"
|
||
|
||
# Code Specialist - DeepSeek Coder 33B (High Priority) - Advanced code tasks
|
||
deepseek-coder-33b:
|
||
path: ollama:deepseek-coder:33b
|
||
type: code
|
||
size_gb: 18.0
|
||
priority: high
|
||
description: "Advanced code specialist model (33B params)"
|
||
|
||
# Code Specialist - Qwen2.5 Coder 32B (High Priority) - Advanced code tasks
|
||
qwen2.5-coder-32b:
|
||
path: ollama:qwen2.5-coder:32b
|
||
type: code
|
||
size_gb: 19.0
|
||
priority: high
|
||
description: "Advanced code specialist model (32.8B params)"
|
||
|
||
# Reasoning Model - DeepSeek R1 70B (High Priority) - Strategic reasoning (large model)
|
||
deepseek-r1-70b:
|
||
path: ollama:deepseek-r1:70b
|
||
type: llm
|
||
size_gb: 42.0
|
||
priority: high
|
||
description: "Strategic reasoning model (70.6B params, quantized)"
|
||
|
||
storage:
|
||
models_dir: /app/models
|
||
cache_dir: /app/cache
|
||
swap_dir: /app/swap
|
||
|
||
ollama:
|
||
url: http://localhost:11434 # Native Ollama on MacBook (via Pieces OS or brew)
|
||
timeout: 300
|
||
|