forked from Karylab-cklius/vllm
[CI] Add gemma-4-E4B-it-assistant to CI gsm8k for GemmaMTP (#49243)
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -2,4 +2,7 @@ model_name: "google/gemma-4-E4B-it-qat-mobile-ct"
|
||||
accuracy_threshold: 0.50
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: "--enforce-eager --max-model-len 4096"
|
||||
server_args: >-
|
||||
--enforce-eager
|
||||
--max-model-len 4096
|
||||
--speculative-config '{"method":"mtp","model":"google/gemma-4-E4B-it-assistant","num_speculative_tokens":4}'
|
||||
|
||||
Reference in New Issue
Block a user