[CI] Small Accuracy Eval Test for Deepseek Model (#24259)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

[CI] Small Accuracy Eval Test for Deepseek Model (#24259)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
3c96e7b8 · Wentao Ye · GitHub · b42566f4 · 3c96e7b8 · 3c96e7b8
Unverified Commit 3c96e7b8 authored Sep 15, 2025 by Wentao Ye Committed by GitHub Sep 15, 2025
Showing with 7 additions and 0 deletions

tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml +6 -0

tests/evals/gsm8k/configs/models-small.txt tests/evals/gsm8k/configs/models-small.txt +1 -0

No files found.
--- a/tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml
+++ b/tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml
+model_name: "RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8"
+accuracy_threshold: 0.72
+num_questions: 1319
+num_fewshot: 5
+max_model_len: 4096
+
--- a/tests/evals/gsm8k/configs/models-small.txt
+++ b/tests/evals/gsm8k/configs/models-small.txt
@@ -3,3 +3,4 @@ Llama-3.2-1B-Instruct-INT8-CT.yaml
 Llama-3-8B-Instruct-nonuniform-CT.yaml
 Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
 Qwen1.5-MoE-W4A16-CT.yaml
+DeepSeek-V2-Lite-Instruct-FP8.yaml