vllm/vllm_v0.10.0/.buildkite/lm-eval-harness/configs/Meta-Llama-3.2-1B-Instruct-...

12 lines
355 B
YAML

# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Llama-3.2-1B-Instruct-FP8 -b "auto" -l 1319 -f 5 -t 1
model_name: "RedHatAI/Llama-3.2-1B-Instruct-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.335
- name: "exact_match,flexible-extract"
value: 0.323
limit: 1319
num_fewshot: 5