atreydesai/augmented-mcqa-together-choices-only
收藏Hugging Face2026-04-03 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/atreydesai/augmented-mcqa-together-choices-only
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: vllm_Qwen_Qwen3-4B-Instruct-2507
features:
- name: id
dtype: string
- name: question_id
dtype: int64
- name: dataset_type
dtype: string
- name: row_index
dtype: int64
- name: sample_id
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
- name: options
list: string
- name: answer_index
dtype: int64
- name: choices_human
list: string
- name: setting
dtype: string
- name: generation_strategy
dtype: string
- name: status
dtype: string
- name: num_human
dtype: int64
- name: num_model
dtype: int64
- name: num_choices
dtype: int64
- name: human_distractors
list: string
- name: model_distractors
list: string
- name: distractors
list: string
- name: options_randomized
list: string
- name: correct_answer_letter
dtype: string
- name: evaluation_is_correct
dtype: bool
- name: evaluation_score
dtype: float64
- name: evaluation_prediction
dtype: string
- name: evaluation_prediction_type
dtype: string
- name: evaluation_raw_output
dtype: string
- name: evaluation_prompt
dtype: string
- name: evaluation_status
dtype: string
- name: evaluation_question_idx
dtype: int64
- name: evaluation_log_path
dtype: string
- name: traces
dtype: string
splits:
- name: human_from_scratch
num_bytes: 6177793
num_examples: 2443
- name: model_from_scratch
num_bytes: 6466187
num_examples: 2443
- name: augment_human
num_bytes: 9487330
num_examples: 2443
- name: augment_model
num_bytes: 9951439
num_examples: 2443
- name: augment_ablation
num_bytes: 9692850
num_examples: 2443
download_size: 27677633
dataset_size: 41775599
- config_name: vllm_allenai_Olmo-3-7B-Instruct
features:
- name: id
dtype: string
- name: question_id
dtype: int64
- name: dataset_type
dtype: string
- name: row_index
dtype: int64
- name: sample_id
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
- name: options
list: string
- name: answer_index
dtype: int64
- name: choices_human
list: string
- name: setting
dtype: string
- name: generation_strategy
dtype: string
- name: status
dtype: string
- name: num_human
dtype: int64
- name: num_model
dtype: int64
- name: num_choices
dtype: int64
- name: human_distractors
list: string
- name: model_distractors
list: string
- name: distractors
list: string
- name: options_randomized
list: string
- name: correct_answer_letter
dtype: string
- name: evaluation_is_correct
dtype: bool
- name: evaluation_score
dtype: float64
- name: evaluation_prediction
dtype: string
- name: evaluation_prediction_type
dtype: string
- name: evaluation_raw_output
dtype: string
- name: evaluation_prompt
dtype: string
- name: evaluation_status
dtype: string
- name: evaluation_question_idx
dtype: int64
- name: evaluation_log_path
dtype: string
- name: traces
dtype: string
splits:
- name: human_from_scratch
num_bytes: 6173213
num_examples: 2443
- name: model_from_scratch
num_bytes: 6461483
num_examples: 2443
- name: augment_human
num_bytes: 9482294
num_examples: 2443
- name: augment_model
num_bytes: 9946465
num_examples: 2443
- name: augment_ablation
num_bytes: 9687886
num_examples: 2443
download_size: 27679593
dataset_size: 41751341
- config_name: vllm_meta-llama_Llama-3.1-8B-Instruct
features:
- name: id
dtype: string
- name: question_id
dtype: int64
- name: dataset_type
dtype: string
- name: row_index
dtype: int64
- name: sample_id
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
- name: options
list: string
- name: answer_index
dtype: int64
- name: choices_human
list: string
- name: setting
dtype: string
- name: generation_strategy
dtype: string
- name: status
dtype: string
- name: num_human
dtype: int64
- name: num_model
dtype: int64
- name: num_choices
dtype: int64
- name: human_distractors
list: string
- name: model_distractors
list: string
- name: distractors
list: string
- name: options_randomized
list: string
- name: correct_answer_letter
dtype: string
- name: evaluation_is_correct
dtype: bool
- name: evaluation_score
dtype: float64
- name: evaluation_prediction
dtype: string
- name: evaluation_prediction_type
dtype: string
- name: evaluation_raw_output
dtype: string
- name: evaluation_prompt
dtype: string
- name: evaluation_status
dtype: string
- name: evaluation_question_idx
dtype: int64
- name: evaluation_log_path
dtype: string
- name: traces
dtype: string
splits:
- name: human_from_scratch
num_bytes: 6189937
num_examples: 2443
- name: model_from_scratch
num_bytes: 6478301
num_examples: 2443
- name: augment_human
num_bytes: 9499510
num_examples: 2443
- name: augment_model
num_bytes: 9963589
num_examples: 2443
- name: augment_ablation
num_bytes: 9705030
num_examples: 2443
download_size: 27677652
dataset_size: 41836367
- config_name: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2
features:
- name: id
dtype: string
- name: question_id
dtype: int64
- name: dataset_type
dtype: string
- name: row_index
dtype: int64
- name: sample_id
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
- name: options
list: string
- name: answer_index
dtype: int64
- name: choices_human
list: string
- name: setting
dtype: string
- name: generation_strategy
dtype: string
- name: status
dtype: string
- name: num_human
dtype: int64
- name: num_model
dtype: int64
- name: num_choices
dtype: int64
- name: human_distractors
list: string
- name: model_distractors
list: string
- name: distractors
list: string
- name: options_randomized
list: string
- name: correct_answer_letter
dtype: string
- name: evaluation_is_correct
dtype: bool
- name: evaluation_score
dtype: float64
- name: evaluation_prediction
dtype: string
- name: evaluation_prediction_type
dtype: string
- name: evaluation_raw_output
dtype: string
- name: evaluation_prompt
dtype: string
- name: evaluation_status
dtype: string
- name: evaluation_question_idx
dtype: int64
- name: evaluation_log_path
dtype: string
- name: traces
dtype: string
splits:
- name: human_from_scratch
num_bytes: 6196989
num_examples: 2443
- name: model_from_scratch
num_bytes: 6485003
num_examples: 2443
- name: augment_human
num_bytes: 9505855
num_examples: 2443
- name: augment_model
num_bytes: 9970127
num_examples: 2443
- name: augment_ablation
num_bytes: 9710995
num_examples: 2443
download_size: 27682591
dataset_size: 41868969
configs:
- config_name: vllm_Qwen_Qwen3-4B-Instruct-2507
data_files:
- split: human_from_scratch
path: vllm_Qwen_Qwen3-4B-Instruct-2507/human_from_scratch-*
- split: model_from_scratch
path: vllm_Qwen_Qwen3-4B-Instruct-2507/model_from_scratch-*
- split: augment_ablation
path: vllm_Qwen_Qwen3-4B-Instruct-2507/augment_ablation-*
- split: augment_human
path: vllm_Qwen_Qwen3-4B-Instruct-2507/augment_human-*
- split: augment_model
path: vllm_Qwen_Qwen3-4B-Instruct-2507/augment_model-*
- config_name: vllm_allenai_Olmo-3-7B-Instruct
data_files:
- split: human_from_scratch
path: vllm_allenai_Olmo-3-7B-Instruct/human_from_scratch-*
- split: model_from_scratch
path: vllm_allenai_Olmo-3-7B-Instruct/model_from_scratch-*
- split: augment_ablation
path: vllm_allenai_Olmo-3-7B-Instruct/augment_ablation-*
- split: augment_human
path: vllm_allenai_Olmo-3-7B-Instruct/augment_human-*
- split: augment_model
path: vllm_allenai_Olmo-3-7B-Instruct/augment_model-*
- config_name: vllm_meta-llama_Llama-3.1-8B-Instruct
data_files:
- split: human_from_scratch
path: vllm_meta-llama_Llama-3.1-8B-Instruct/human_from_scratch-*
- split: model_from_scratch
path: vllm_meta-llama_Llama-3.1-8B-Instruct/model_from_scratch-*
- split: augment_ablation
path: vllm_meta-llama_Llama-3.1-8B-Instruct/augment_ablation-*
- split: augment_human
path: vllm_meta-llama_Llama-3.1-8B-Instruct/augment_human-*
- split: augment_model
path: vllm_meta-llama_Llama-3.1-8B-Instruct/augment_model-*
- config_name: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2
data_files:
- split: human_from_scratch
path: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2/human_from_scratch-*
- split: model_from_scratch
path: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2/model_from_scratch-*
- split: augment_ablation
path: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2/augment_ablation-*
- split: augment_human
path: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2/augment_human-*
- split: augment_model
path: vllm_nvidia_NVIDIA-Nemotron-Nano-9B-v2/augment_model-*
---
提供机构:
atreydesai



