noneUsername's picture
Create README.md
1797b72 verified
metadata
base_model:
  - VAGOsolutions/SauerkrautLM-v2-14b-SFT

vllm (pretrained=/root/autodl-tmp/SauerkrautLM-v2-14b-SFT,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 0.88 ± 0.0206
strict-match 5 exact_match 0.86 ± 0.0220

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 0.908 ± 0.0183
strict-match 5 exact_match 0.900 ± 0.0190