speculator_benchmarks

B待确认Benchmark

性能/成本推理速度开放apache-2.0

发布方：RedHatAI

热度18.6▼ 0.2

Hugging Face

下载量 · 30天

5,216

Hugging Face

GitHub Stars

—

代码仓库

论文被引

—

Semantic Scholar

跑分模型 · 30天

—

Leaderboard results

简介

This dataset contains dataset splits for evaluating speculative decoding algorithms on different tasks. File: Coding: HumanEval.jsonl Math: math_reasoning.jsonl Question Answering: qa.jsonl MT_bench: question.jsonl Retrieval-Augmented Generation: rag.jsonl Summarization: summarization.jsonl Translation (German to English): translation.jsonl Writing: writing.jsonl The data comes from two sources: https://github.com/openai/human-eval (1). (The MIT License)… See the full description on the dataset page: https://huggingface.co/datasets/RedHatAI/speculator_benchmarks.