lm_eval --model vllm --model_args pretrained=nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V,kv_cache_dtype=fp8,add_bos_token=True --tasks gsm8k --num_fewshot 5 --batch_size auto
vllm (pretrained=nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V,kv_cache_dtype=fp8,add_bos_token=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.7748|± |0.0115|
| | |strict-match | 5|exact_match|↑ |0.7763|± |0.0115|
