vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,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 ↑ 0.488 ± 0.0317
strict-match 5 exact_match ↑ 0.740 ± 0.0278

vllm (pretrained=/root/autodl-tmp/QwQ-32B-abliterated-awq,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 ↑ 0.47 ± 0.0223
strict-match 5 exact_match ↑ 0.72 ± 0.0201
Groups Version Filter n-shot Metric Value Stderr
mmlu 2 none acc ↑ 0.8070 ± 0.0128
- humanities 2 none acc ↑ 0.8051 ± 0.0253
- other 2 none acc ↑ 0.7744 ± 0.0295
- social sciences 2 none acc ↑ 0.8722 ± 0.0244
- stem 2 none acc ↑ 0.7895 ± 0.0229
Downloads last month
11
Safetensors
Model size
5.73B params
Tensor type
I32
·
FP16
·
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/QwQ-32B-abliterated-AWQ-INT4-float16

Base model

Qwen/Qwen2.5-32B
Finetuned
Qwen/QwQ-32B
Quantized
(9)
this model