该数据集包含一个名为Prompt的字段和100个名为Generated_Text_X的字段，其中X从1到100。这些字段的数据类型均为字符串。数据集包含一个名为train的分割，该分割包含4098个样本，总大小为603522813字节。数据集的下载大小为266877344字节，总数据集大小为603522813字节。

Hugging Face2024-05-07 更新110

ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-arc_challenge

机器学习

自然语言处理

--- dataset_info: features: - name: question_id dtype: string - name: chosen sequence: float32 - name: rejected sequence: float32 splits: - name: train num_bytes: 109930520

Hugging Face2024-05-05 更新110

ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-reward_bench

模型评估

自然语言处理

--- dataset_info: features: - name: question_id dtype: string - name: chosen sequence: float32 - name: rejected sequence: float32 splits: - name: train num_bytes: 134282154

Hugging Face2024-05-05 更新120

ura-hcmut/Pre-computed-embedding-Meta-Llama-3-8B-Instruct-reward_bench

机器学习

自然语言处理

--- dataset_info: features: - name: question_id dtype: string - name: chosen sequence: float32 - name: rejected sequence: float32 splits: - name: train num_bytes: 134282154

Hugging Face2024-05-05 更新110

ura-hcmut/PhoMT

资源简介：

相关数据集