noneUsername's picture
Create README.md
43077c6 verified
metadata
base_model:
  - v000000/Qwen2.5-14B-Gutenberg-1e-Delta

vllm (pretrained=/root/autodl-tmp/output,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match 0.608 ± 0.0309
strict-match 5 exact_match 0.812 ± 0.0248

vllm (pretrained=/root/autodl-tmp/Qwen2.5-14B-Gutenberg-1e-Delta,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match 0.564 ± 0.0314
strict-match 5 exact_match 0.836 ± 0.0235