vllm (pretrained=/root/autodl-tmp/Mistral-Small-24B-Instruct-2501-writer,add_bos_token=true,max_model_len=4096,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 ↑ 0.924 ± 0.0168
strict-match 5 exact_match ↑ 0.920 ± 0.0172

vllm (pretrained=/root/autodl-tmp/Mistral-Small-24B-Instruct-2501-writer,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.918 ± 0.0123
strict-match 5 exact_match ↑ 0.908 ± 0.0129

vllm (pretrained=/root/autodl-tmp/Mistral-Small-24B-Instruct-2501-writer,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1

Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7977 ± 0.0131
- humanities 2 none acc ↑ 0.8256 ± 0.0263
- other 2 none acc ↑ 0.8205 ± 0.0265
- social sciences 2 none acc ↑ 0.8556 ± 0.0256
- stem 2 none acc ↑ 0.7263 ± 0.0249

vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=4096,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 ↑ 0.92 ± 0.0172
strict-match 5 exact_match ↑ 0.92 ± 0.0172

vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.910 ± 0.0128
strict-match 5 exact_match ↑ 0.906 ± 0.0131

vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1

Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7836 ± 0.0133
- humanities 2 none acc ↑ 0.8103 ± 0.0267
- other 2 none acc ↑ 0.7949 ± 0.0271
- social sciences 2 none acc ↑ 0.8556 ± 0.0252
- stem 2 none acc ↑ 0.7123 ± 0.0257

vllm (pretrained=/root/autodl-tmp/86-256,add_bos_token=true,max_model_len=4096,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 ↑ 0.928 ± 0.0164
strict-match 5 exact_match ↑ 0.924 ± 0.0168

vllm (pretrained=/root/autodl-tmp/86-256,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.928 ± 0.0116
strict-match 5 exact_match ↑ 0.920 ± 0.0121

vllm (pretrained=/root/autodl-tmp/86-256,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1

Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7942 ± 0.0131
- humanities 2 none acc ↑ 0.8103 ± 0.0270
- other 2 none acc ↑ 0.7949 ± 0.0280
- social sciences 2 none acc ↑ 0.8556 ± 0.0252
- stem 2 none acc ↑ 0.7439 ± 0.0242
Downloads last month
1
Safetensors
Model size
23.6B params
Tensor type
FP16
·
I8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for noneUsername/Mistral-Small-24B-Instruct-2501-writer-W8A8-better