12 lines
324 B
Markdown
12 lines
324 B
Markdown
|
# trader-flow — Automaton Configuration
|
||
|
|
|
||
|
|
## VRAM Configuration
|
||
|
|
- **Auto-detect**: Yes
|
||
|
|
- **Target context**: 58k tokens
|
||
|
|
- **Headroom**: 25%
|
||
|
|
- **Max peak context per sub-task**: 43k tokens
|
||
|
|
|
||
|
|
## Model Configuration
|
||
|
|
# Uses models.json for model divergence enforcement.
|
||
|
|
# Default model is read from models.json's "default" key.
|