vllm/vllm_v0.10.0/.buildkite/lm-eval-harness/configs/Qwen2.5-VL-3B-Instruct-FP8-...

12 lines
369 B
YAML

# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic -b auto -l 1319 -f 5 -t 1
model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.47
- name: "exact_match,flexible-extract"
value: 0.64
limit: 1319
num_fewshot: 5