atreydesai/augmented-mcqa-gemini-full-question
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-gemini-full-question
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: 6522026
num_examples: 2443
- name: model_from_scratch
num_bytes: 6743054
num_examples: 2443
- name: augment_human
num_bytes: 9663768
num_examples: 2443
- name: augment_model
num_bytes: 10124054
num_examples: 2443
- name: augment_ablation
num_bytes: 9973413
num_examples: 2443
download_size: 29424802
dataset_size: 43026315
- 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: 6495309
num_examples: 2443
- name: model_from_scratch
num_bytes: 6716318
num_examples: 2443
- name: augment_human
num_bytes: 9651125
num_examples: 2443
- name: augment_model
num_bytes: 10112200
num_examples: 2443
- name: augment_ablation
num_bytes: 9960915
num_examples: 2443
download_size: 29426801
dataset_size: 42935867
- 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: 6511233
num_examples: 2443
- name: model_from_scratch
num_bytes: 6732323
num_examples: 2443
- name: augment_human
num_bytes: 9668422
num_examples: 2443
- name: augment_model
num_bytes: 10129800
num_examples: 2443
- name: augment_ablation
num_bytes: 9977918
num_examples: 2443
download_size: 29424610
dataset_size: 43019696
- 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: 6520430
num_examples: 2443
- name: model_from_scratch
num_bytes: 6741929
num_examples: 2443
- name: augment_human
num_bytes: 9676228
num_examples: 2443
- name: augment_model
num_bytes: 10137534
num_examples: 2443
- name: augment_ablation
num_bytes: 9985599
num_examples: 2443
download_size: 29427421
dataset_size: 43061720
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



