fix: reduce max_tokens to 2048 to fit 8192 context window
This commit is contained in:
@@ -6,7 +6,7 @@
|
|||||||
UPDATE ai_agents
|
UPDATE ai_agents
|
||||||
SET model_provider = 'vllm',
|
SET model_provider = 'vllm',
|
||||||
model_name = 'AxionML/Qwen3.5-9B-NVFP4',
|
model_name = 'AxionML/Qwen3.5-9B-NVFP4',
|
||||||
max_tokens = 4096,
|
max_tokens = 2048,
|
||||||
updated_at = NOW()
|
updated_at = NOW()
|
||||||
WHERE slug IN ('document-extractor', 'event-classifier', 'thesis-rewriter')
|
WHERE slug IN ('document-extractor', 'event-classifier', 'thesis-rewriter')
|
||||||
AND source = 'system'
|
AND source = 'system'
|
||||||
|
|||||||
Reference in New Issue
Block a user