multi-domain-reasoning/commonsense_qa_eval
收藏Hugging Face2024-12-24 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/multi-domain-reasoning/commonsense_qa_eval
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
features:
- name: id
dtype: string
- name: question
dtype: string
- name: question_concept
dtype: string
- name: choices
sequence:
- name: label
dtype: string
- name: text
dtype: string
- name: answerKey
dtype: string
- name: input
dtype: string
- name: extracted_baseline_llama_1b
dtype: string
- name: reasoning_64_a128_mix_mmlu_csqa_gsm8k_even
dtype: string
- name: baseline_llama_1b
dtype: string
- name: output_w_reasoning_llama_1b
dtype: string
- name: extracted_output_w_reasoning_llama_1b
dtype: string
- name: eval_baseline_vs_mixed_reasoning
dtype: string
- name: baseline_phi_3.5_mini
dtype: string
- name: output_w_reasoning_phi_3.5_mini
dtype: string
- name: eval_baseline_vs_mixed_reasoning_phi_3.5_mini
dtype: string
- name: reasoning_64_a128_mix_mmlu_csqa_gsm8k_even_phi_3.5_mini
dtype: string
- name: baseline_llama_3.1_8b
dtype: string
- name: reasoning_64_a128_mix_mmlu_csqa_gsm8k_even_llama_3.1_8b
dtype: string
- name: output_w_reasoning_llama_3.1_8b
dtype: string
- name: eval_baseline_vs_mixed_reasoning_llama_3.1_8b
dtype: string
splits:
- name: validation
num_bytes: 23401655
num_examples: 1221
download_size: 11091498
dataset_size: 23401655
configs:
- config_name: default
data_files:
- split: validation
path: data/validation-*
---
提供机构：
multi-domain-reasoning
