five

bigcode/bigcodebench-instruct-perf

收藏
Hugging Face2024-07-02 更新2024-07-06 收录
下载链接:
https://hf-mirror.com/datasets/bigcode/bigcodebench-instruct-perf
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: task_id dtype: string - name: status dtype: int64 splits: - name: Magicoder_S_DS_6.7B num_bytes: 31950 num_examples: 1140 - name: StarCoder2_15B_Instruct_v0.1 num_bytes: 31950 num_examples: 1140 - name: CodeGemma_7B_Instruct num_bytes: 31950 num_examples: 1140 - name: GPT_3.5_Turbo_0125 num_bytes: 31950 num_examples: 1140 - name: GPT_4o_2024_05_13 num_bytes: 31950 num_examples: 1140 - name: GPT_4_Turbo_2024_04_09 num_bytes: 31950 num_examples: 1140 - name: GPT_4_0613 num_bytes: 31950 num_examples: 1140 - name: CodeLlama_7B_Instruct num_bytes: 31950 num_examples: 1140 - name: CodeLlama_13B_Instruct num_bytes: 31950 num_examples: 1140 - name: Mistral_Large_2402 num_bytes: 31950 num_examples: 1140 - name: Mistral_Small_2402 num_bytes: 31950 num_examples: 1140 - name: Mixtral_8x22B_Instruct num_bytes: 31950 num_examples: 1140 - name: CodeLlama_34B_Instruct num_bytes: 31950 num_examples: 1140 - name: CodeLlama_70B_Instruct num_bytes: 31950 num_examples: 1140 - name: CodeQwen1.5_7B_Chat num_bytes: 31950 num_examples: 1140 - name: Qwen1.5_110B_Chat num_bytes: 31950 num_examples: 1140 - name: Qwen1.5_72B_Chat num_bytes: 31950 num_examples: 1140 - name: Qwen1.5_32B_Chat num_bytes: 31950 num_examples: 1140 - name: DeepSeek_V2_Chat num_bytes: 31950 num_examples: 1140 - name: DeepSeek_Coder_1.3B_Instruct num_bytes: 31950 num_examples: 1140 - name: DeepSeek_Coder_33B_Instruct num_bytes: 31950 num_examples: 1140 - name: DeepSeek_Coder_6.7B_Instruct num_bytes: 31950 num_examples: 1140 - name: Llama_3_70B_Instruct num_bytes: 31950 num_examples: 1140 - name: Llama_3_8B_Instruct num_bytes: 31950 num_examples: 1140 - name: Granite_Code_20B_Instruct num_bytes: 31950 num_examples: 1140 - name: Granite_Code_34B_Instruct num_bytes: 31950 num_examples: 1140 - name: Claude_3_Haiku_20240307 num_bytes: 31950 num_examples: 1140 - name: Claude_3_Sonnet_20240229 num_bytes: 31950 num_examples: 1140 - name: Claude_3_Opus_20240229 num_bytes: 31950 num_examples: 1140 - name: Yi_1.5_34B_Chat num_bytes: 31950 num_examples: 1140 - name: Yi_1.5_9B_Chat num_bytes: 31950 num_examples: 1140 - name: Yi_1.5_6B_Chat num_bytes: 31950 num_examples: 1140 - name: Qwen2_57B_A14B num_bytes: 31950 num_examples: 1140 - name: Qwen2_7B_Instruct num_bytes: 31950 num_examples: 1140 - name: Qwen2_72B_Chat num_bytes: 31950 num_examples: 1140 - name: Gemini_1.5_Pro_API_0514 num_bytes: 31950 num_examples: 1140 - name: Gemini_1.5_Flash_API_0514 num_bytes: 31950 num_examples: 1140 - name: OpenCodeInterpreter_DS_6.7B num_bytes: 31950 num_examples: 1140 - name: OpenCodeInterpreter_DS_1.3B num_bytes: 31950 num_examples: 1140 - name: Phi_3_medium_128k_instruct num_bytes: 31950 num_examples: 1140 - name: Phi_3_small_128k_instruct num_bytes: 31950 num_examples: 1140 - name: Mistral_7B_Instruct_v0.3 num_bytes: 31950 num_examples: 1140 - name: Command_R_plus num_bytes: 31950 num_examples: 1140 - name: DeepSeek_Coder_V2_Instruct num_bytes: 31950 num_examples: 1140 - name: DeepSeek_Coder_V2_Lite_Instruct num_bytes: 31950 num_examples: 1140 - name: Claude_3.5_Sonnet_20240620 num_bytes: 31950 num_examples: 1140 - name: Hermes_2_Theta_Llama_3_70B num_bytes: 31950 num_examples: 1140 - name: WaveCoder_Ultra_6.7B num_bytes: 31950 num_examples: 1140 - name: Gemma_2_9B_Instruct num_bytes: 31950 num_examples: 1140 - name: AutoCoder num_bytes: 31950 num_examples: 1140 - name: AutoCoder_S_6.7B num_bytes: 31950 num_examples: 1140 - name: AutoCoder_QW_7B num_bytes: 31950 num_examples: 1140 download_size: 482294 dataset_size: 1661400 configs: - config_name: default data_files: - split: Magicoder_S_DS_6.7B path: data/Magicoder_S_DS_6.7B-* - split: StarCoder2_15B_Instruct_v0.1 path: data/StarCoder2_15B_Instruct_v0.1-* - split: CodeGemma_7B_Instruct path: data/CodeGemma_7B_Instruct-* - split: GPT_3.5_Turbo_0125 path: data/GPT_3.5_Turbo_0125-* - split: GPT_4o_2024_05_13 path: data/GPT_4o_2024_05_13-* - split: GPT_4_Turbo_2024_04_09 path: data/GPT_4_Turbo_2024_04_09-* - split: GPT_4_0613 path: data/GPT_4_0613-* - split: CodeLlama_7B_Instruct path: data/CodeLlama_7B_Instruct-* - split: CodeLlama_13B_Instruct path: data/CodeLlama_13B_Instruct-* - split: Mistral_Large_2402 path: data/Mistral_Large_2402-* - split: Mistral_Small_2402 path: data/Mistral_Small_2402-* - split: Mixtral_8x22B_Instruct path: data/Mixtral_8x22B_Instruct-* - split: CodeLlama_34B_Instruct path: data/CodeLlama_34B_Instruct-* - split: CodeLlama_70B_Instruct path: data/CodeLlama_70B_Instruct-* - split: CodeQwen1.5_7B_Chat path: data/CodeQwen1.5_7B_Chat-* - split: Qwen1.5_110B_Chat path: data/Qwen1.5_110B_Chat-* - split: Qwen1.5_72B_Chat path: data/Qwen1.5_72B_Chat-* - split: Qwen1.5_32B_Chat path: data/Qwen1.5_32B_Chat-* - split: DeepSeek_V2_Chat path: data/DeepSeek_V2_Chat-* - split: DeepSeek_Coder_1.3B_Instruct path: data/DeepSeek_Coder_1.3B_Instruct-* - split: DeepSeek_Coder_33B_Instruct path: data/DeepSeek_Coder_33B_Instruct-* - split: DeepSeek_Coder_6.7B_Instruct path: data/DeepSeek_Coder_6.7B_Instruct-* - split: Llama_3_70B_Instruct path: data/Llama_3_70B_Instruct-* - split: Llama_3_8B_Instruct path: data/Llama_3_8B_Instruct-* - split: Granite_Code_20B_Instruct path: data/Granite_Code_20B_Instruct-* - split: Granite_Code_34B_Instruct path: data/Granite_Code_34B_Instruct-* - split: Claude_3_Haiku_20240307 path: data/Claude_3_Haiku_20240307-* - split: Claude_3_Sonnet_20240229 path: data/Claude_3_Sonnet_20240229-* - split: Claude_3_Opus_20240229 path: data/Claude_3_Opus_20240229-* - split: Yi_1.5_34B_Chat path: data/Yi_1.5_34B_Chat-* - split: Yi_1.5_9B_Chat path: data/Yi_1.5_9B_Chat-* - split: Yi_1.5_6B_Chat path: data/Yi_1.5_6B_Chat-* - split: Qwen2_57B_A14B path: data/Qwen2_57B_A14B-* - split: Qwen2_7B_Instruct path: data/Qwen2_7B_Instruct-* - split: Qwen2_72B_Chat path: data/Qwen2_72B_Chat-* - split: Gemini_1.5_Pro_API_0514 path: data/Gemini_1.5_Pro_API_0514-* - split: Gemini_1.5_Flash_API_0514 path: data/Gemini_1.5_Flash_API_0514-* - split: OpenCodeInterpreter_DS_6.7B path: data/OpenCodeInterpreter_DS_6.7B-* - split: OpenCodeInterpreter_DS_1.3B path: data/OpenCodeInterpreter_DS_1.3B-* - split: Phi_3_medium_128k_instruct path: data/Phi_3_medium_128k_instruct-* - split: Phi_3_small_128k_instruct path: data/Phi_3_small_128k_instruct-* - split: Mistral_7B_Instruct_v0.3 path: data/Mistral_7B_Instruct_v0.3-* - split: Command_R_plus path: data/Command_R_plus-* - split: DeepSeek_Coder_V2_Instruct path: data/DeepSeek_Coder_V2_Instruct-* - split: DeepSeek_Coder_V2_Lite_Instruct path: data/DeepSeek_Coder_V2_Lite_Instruct-* - split: Claude_3.5_Sonnet_20240620 path: data/Claude_3.5_Sonnet_20240620-* - split: Hermes_2_Theta_Llama_3_70B path: data/Hermes_2_Theta_Llama_3_70B-* - split: WaveCoder_Ultra_6.7B path: data/WaveCoder_Ultra_6.7B-* - split: Gemma_2_9B_Instruct path: data/Gemma_2_9B_Instruct-* - split: AutoCoder path: data/AutoCoder-* - split: AutoCoder_S_6.7B path: data/AutoCoder_S_6.7B-* - split: AutoCoder_QW_7B path: data/AutoCoder_QW_7B-* ---
提供机构:
bigcode
原始信息汇总

数据集概述

数据集特征

  • task_id: 数据类型为 string
  • status: 数据类型为 int64

数据集分割

数据集包含多个分割,每个分割具有相同的数据量和样本数:

  • 名称: 每个分割的名称。
  • 字节数: 每个分割包含 31950 字节。
  • 样本数: 每个分割包含 1140 个样本。

具体分割列表

  • Magicoder_S_DS_6.7B
  • StarCoder2_15B_Instruct_v0.1
  • CodeGemma_7B_Instruct
  • GPT_3.5_Turbo_0125
  • GPT_4o_2024_05_13
  • GPT_4_Turbo_2024_04_09
  • GPT_4_0613
  • CodeLlama_7B_Instruct
  • CodeLlama_13B_Instruct
  • Mistral_Large_2402
  • Mistral_Small_2402
  • Mixtral_8x22B_Instruct
  • CodeLlama_34B_Instruct
  • CodeLlama_70B_Instruct
  • CodeQwen1.5_7B_Chat
  • Qwen1.5_110B_Chat
  • Qwen1.5_72B_Chat
  • Qwen1.5_32B_Chat
  • DeepSeek_V2_Chat
  • DeepSeek_Coder_1.3B_Instruct
  • DeepSeek_Coder_33B_Instruct
  • DeepSeek_Coder_6.7B_Instruct
  • Llama_3_70B_Instruct
  • Llama_3_8B_Instruct
  • Granite_Code_20B_Instruct
  • Granite_Code_34B_Instruct
  • Claude_3_Haiku_20240307
  • Claude_3_Sonnet_20240229
  • Claude_3_Opus_20240229
  • Yi_1.5_34B_Chat
  • Yi_1.5_9B_Chat
  • Yi_1.5_6B_Chat
  • Qwen2_57B_A14B
  • Qwen2_7B_Instruct
  • Qwen2_72B_Chat
  • Gemini_1.5_Pro_API_0514
  • Gemini_1.5_Flash_API_0514
  • OpenCodeInterpreter_DS_6.7B
  • OpenCodeInterpreter_DS_1.3B
  • Phi_3_medium_128k_instruct
  • Phi_3_small_128k_instruct
  • Mistral_7B_Instruct_v0.3
  • Command_R_plus
  • DeepSeek_Coder_V2_Instruct
  • DeepSeek_Coder_V2_Lite_Instruct
  • Claude_3.5_Sonnet_20240620
  • Hermes_2_Theta_Llama_3_70B
  • WaveCoder_Ultra_6.7B
  • Gemma_2_9B_Instruct
  • AutoCoder
  • AutoCoder_S_6.7B
  • AutoCoder_QW_7B

数据集大小

  • 下载大小: 482294 字节。
  • 数据集大小: 1661400 字节。

配置

  • 配置名称: default
  • 数据文件路径: 每个分割对应的数据文件路径。
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作