xc-llm-ascend/tests/e2e/models/configs/InternVL3_5-8B-hf.yaml

model_name: "OpenGVLab/InternVL3_5-8B-hf"
hardware: "Atlas A2 Series"
model: "vllm-vlm"
tasks:
  - name: "mmmu_val"
    metrics:
    - name: "acc,none"
      value: 0.58
max_model_len: 40960
trust_remote_code: True
[Test][Accuracy] Add accuracy evaluation config for InternVL3_5-8B (#3964) ### What this PR does / why we need it? To continuously monitor the accuracy of the InternVL3_5-8B model, this PR adds the corresponding configuration file to the CI. We need to add the `-hf` suffix to avoid incompatibility with the `lm-eval` preprocessor. ### How was this patch tested? `pytest -sv ./tests/e2e/models/test_lm_eval_correctness.py --config ./tests/e2e/models/configs/InternVL3_5-8B.yaml` - vLLM version: v0.11.0 - vLLM main: https://github.com/vllm-project/vllm/commit/83f478bb19489b41e9d208b47b4bb5a95ac171ac Signed-off-by: gcanlin <canlinguosdu@gmail.com> 2025-11-12 09:05:55 +08:00			`model_name: "OpenGVLab/InternVL3_5-8B-hf"`
			`hardware: "Atlas A2 Series"`
			`model: "vllm-vlm"`
			`tasks:`
			`- name: "mmmu_val"`
			`metrics:`
			`- name: "acc,none"`
			`value: 0.58`
			`max_model_len: 40960`
			`trust_remote_code: True`