2025-04-27 02:25:05 +08:00
|
|
|
# For vllm script, with -t option (tensor parallel size).
|
2024-07-13 23:03:58 -04:00
|
|
|
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m deepseek-ai/DeepSeek-V2-Lite-Chat -b "auto" -l 1000 -f 5 -t 2
|
|
|
|
|
model_name: "deepseek-ai/DeepSeek-V2-Lite-Chat"
|
|
|
|
|
tasks:
|
|
|
|
|
- name: "gsm8k"
|
|
|
|
|
metrics:
|
|
|
|
|
- name: "exact_match,strict-match"
|
|
|
|
|
value: 0.671
|
|
|
|
|
- name: "exact_match,flexible-extract"
|
|
|
|
|
value: 0.664
|
|
|
|
|
limit: 1000
|
|
|
|
|
num_fewshot: 5
|
2024-08-06 11:16:53 -04:00
|
|
|
trust_remote_code: True
|
