vllm/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml

12 lines
429 B
YAML
Raw Normal View History

# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.728
- name: "exact_match,flexible-extract"
value: 0.728
limit: 250
num_fewshot: 5