selected 70-1024-df10-u2k

vllm (pretrained=/root/autodl-tmp/Cydonia-24B-v2,add_bos_token=true,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 ↑ 0.912 ± 0.018
strict-match 5 exact_match ↑ 0.912 ± 0.018

vllm (pretrained=/root/autodl-tmp/Cydonia-24B-v2,add_bos_token=true,max_model_len=2048,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 ↑ 0.904 ± 0.0132
strict-match 5 exact_match ↑ 0.894 ± 0.0138

vllm (pretrained=/root/autodl-tmp/Cydonia-24B-v2,add_bos_token=true,max_model_len=700,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 ↑ 0.8205 ± 0.0257
- other 2 none acc ↑ 0.8103 ± 0.0271
- social sciences 2 none acc ↑ 0.8500 ± 0.0257
- stem 2 none acc ↑ 0.7298 ± 0.0249

vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=2048), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 1

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.892 ± 0.0197
strict-match 5 exact_match ↑ 0.880 ± 0.0206

vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=2048,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 ↑ 0.894 ± 0.0138
strict-match 5 exact_match ↑ 0.876 ± 0.0148

vllm (pretrained=/root/autodl-tmp/70-512-df10,add_bos_token=true,max_model_len=800,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 ↑ 0.7895 ± 0.0132
- humanities 2 none acc ↑ 0.8103 ± 0.0257
- other 2 none acc ↑ 0.7949 ± 0.0280
- social sciences 2 none acc ↑ 0.8722 ± 0.0242
- stem 2 none acc ↑ 0.7193 ± 0.0258

vllm (pretrained=/root/autodl-tmp/70-1536-df10,add_bos_token=true,max_model_len=2048), 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 ↑ 0.888 ± 0.0200
strict-match 5 exact_match ↑ 0.876 ± 0.0209

vllm (pretrained=/root/autodl-tmp/70-1536-df10,add_bos_token=true,max_model_len=2048,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 ↑ 0.884 ± 0.0143
strict-match 5 exact_match ↑ 0.856 ± 0.0157

vllm (pretrained=/root/autodl-tmp/70-1536-df10,add_bos_token=true,max_model_len=800,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: auto

Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7906 ± 0.0133
- humanities 2 none acc ↑ 0.8154 ± 0.0266
- other 2 none acc ↑ 0.7949 ± 0.0282
- social sciences 2 none acc ↑ 0.8611 ± 0.0248
- stem 2 none acc ↑ 0.7263 ± 0.0251

vllm (pretrained=/root/autodl-tmp/70-1024-df10-u2k,add_bos_token=true,max_model_len=2048), 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 ↑ 0.884 ± 0.0203
strict-match 5 exact_match ↑ 0.864 ± 0.0217

vllm (pretrained=/root/autodl-tmp/70-1024-df10-u2k,add_bos_token=true,max_model_len=2048,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 ↑ 0.886 ± 0.0142
strict-match 5 exact_match ↑ 0.858 ± 0.0156

vllm (pretrained=/root/autodl-tmp/70-1024-df10-u2k,add_bos_token=true,max_model_len=800,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: auto

Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.7965 ± 0.0130
- humanities 2 none acc ↑ 0.8256 ± 0.0259
- other 2 none acc ↑ 0.8000 ± 0.0268
- social sciences 2 none acc ↑ 0.8778 ± 0.0243
- stem 2 none acc ↑ 0.7228 ± 0.0253
Downloads last month
6
Safetensors
Model size
23.6B params
Tensor type
BF16
·
I8
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for noneUsername/Cydonia-24B-v2-W8A8

Quantized
(21)
this model