We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 5191dab commit 673610eCopy full SHA for 673610e
examples/mlx_kernel_optimization/config.yaml
@@ -12,7 +12,7 @@ llm:
12
api_base: "https://generativelanguage.googleapis.com/v1beta/openai/"
13
temperature: 0.7
14
top_p: 0.95
15
- max_tokens: 8192
+ max_tokens: 16000 # thinking models require sufficient tokens otherwise the responses are trucated or empty
16
timeout: 600
17
18
# Prompt configuration for MLX training optimization
0 commit comments