no-mistakes(review): Align Rule 8 max_context_window rationale with pool floor
This commit is contained in:
@@ -284,7 +284,7 @@ The following MUST be identical across ALL profiles:
|
|||||||
- For 128K context window: `threshold: 0.65` (fires at ~85K tokens)
|
- For 128K context window: `threshold: 0.65` (fires at ~85K tokens)
|
||||||
- Do NOT use `threshold: 0.25` — this fires at 65K, causing premature context loss
|
- Do NOT use `threshold: 0.25` — this fires at 65K, causing premature context loss
|
||||||
- Do NOT use `threshold: 0.80` — this delays until ~105K, leaving only 23K margin
|
- Do NOT use `threshold: 0.80` — this delays until ~105K, leaving only 23K margin
|
||||||
- `max_context_window: 131072` MUST match the model's actual capacity (128K)
|
- `max_context_window: 131072` MUST stay at the pool floor (NVIDIA hosts 128K; Strix Halo 256K)
|
||||||
- See `devops-hermes-compression` skill for full reference
|
- See `devops-hermes-compression` skill for full reference
|
||||||
|
|
||||||
### Rule 9: Compression Threshold for 128K Models
|
### Rule 9: Compression Threshold for 128K Models
|
||||||
|
|||||||
Reference in New Issue
Block a user