vllm/.buildkite/lm-eval-harness/configs/Mixtral-8x7B-Instruct-v0.1.yaml
Robert Shaw 75aa1442db
[ CI/Build ] LM Eval Harness Based CI Testing (#5838)
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
2024-06-29 13:04:30 -04:00

12 lines
353 B
YAML

# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1 -b 32 -l 250 -f 5 -t 4
model_name: "mistralai/Mixtral-8x7B-Instruct-v0.1"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.616
- name: "exact_match,flexible-extract"
value: 0.632
limit: 250
num_fewshot: 5