Name: ENSEONG/delta-Qwen2.5-1.5B-Instruct-Prm-Skywork-Qwen2.5-1.5B-dvts-completions
Creator: ENSEONG
Published: 2025-12-11 06:51:59
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/ENSEONG/delta-Qwen2.5-1.5B-Instruct-Prm-Skywork-Qwen2.5-1.5B-dvts-completions

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-0.1 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 58197847 num_examples: 500 download_size: 11933187 dataset_size: 58197847 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-0.5 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 57303024 num_examples: 500 download_size: 11639782 dataset_size: 57303024 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-1.0 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 57334123 num_examples: 500 download_size: 11704432 dataset_size: 57334123 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-1.5 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 57702632 num_examples: 500 download_size: 11506123 dataset_size: 57702632 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-10.0 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 56944295 num_examples: 500 download_size: 11634724 dataset_size: 56944295 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-2.0 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 57389598 num_examples: 500 download_size: 11555661 dataset_size: 57389598 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-2.5 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 57369130 num_examples: 500 download_size: 11680561 dataset_size: 57369130 - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-3.0 features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: subject dtype: string - name: level dtype: int64 - name: unique_id dtype: string - name: completions list: string - name: pred dtype: string - name: completion_tokens dtype: int64 - name: scores list: list: float64 - name: entropies list: list: float64 - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: agg_scores list: float64 - name: pred_weighted@1 dtype: string - name: pred_maj@1 dtype: string - name: pred_naive@1 dtype: string - name: pred_weighted@2 dtype: string - name: pred_maj@2 dtype: string - name: pred_naive@2 dtype: string - name: pred_weighted@4 dtype: string - name: pred_maj@4 dtype: string - name: pred_naive@4 dtype: string - name: pred_weighted@8 dtype: string - name: pred_maj@8 dtype: string - name: pred_naive@8 dtype: string - name: pred_weighted@16 dtype: string - name: pred_maj@16 dtype: string - name: pred_naive@16 dtype: string - name: pred_weighted@32 dtype: string - name: pred_maj@32 dtype: string - name: pred_naive@32 dtype: string - name: pred_weighted@64 dtype: string - name: pred_maj@64 dtype: string - name: pred_naive@64 dtype: string splits: - name: train num_bytes: 57021794 num_examples: 500 download_size: 11647972 dataset_size: 57021794 configs: - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-0.1 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-0.1/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-0.5 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-0.5/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-1.0 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-1.0/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-1.5 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-1.5/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-10.0 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-10.0/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-2.0 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-2.0/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-2.5 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-2.5/train-* - config_name: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-3.0 data_files: - split: train path: HuggingFaceH4_MATH-500--T-0.8--top_p-1.0--n-64--m-4--iters-40--look-0--seed-0--agg_strategy--last--delta_sel--beta-3.0/train-* ---

应用场景：