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 252ee8f commit 2ce535fCopy full SHA for 2ce535f
11-embeddings-reranker-classification-tensorrt/Briton-qwen-qwq-32b-reasoning-fp8/config.yaml
@@ -3,15 +3,15 @@ environment_variables: {}
3
external_package_dirs: []
4
model_metadata:
5
example_model_input:
6
- max_tokens: 512
+ max_tokens: 2048
7
messages:
8
- content: Tell me everything you know about optimized inference.
9
role: user
10
stream: true
11
temperature: 0.5
12
tags:
13
- openai-compatible
14
-model_name: Briton-qwen-qwq-32b-reasoning-fp8-truss-example
+model_name: Qwen QwQ 32B
15
python_version: py39
16
requirements: []
17
resources:
0 commit comments