Gemma2-27B

基础大模型

Gemma2-27B

Release date: 2024-05-14更新于: 2024-05-15 08:46:15599

Live demo

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemma2-27B

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

4K tokens

Max output length

No data

Model type

基础大模型

Release date

2024-05-14

Model file size

54GB

MoE architecture

Total params / Active params

270.0B / N/A

Knowledge cutoff

No data

Gemma2-27B

Open source & experience

Code license

Apache 2.0

Weights license

Gemma Terms of Use- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

Gemma2-27B

Benchmark Results

Gemma2-27B currently shows benchmark results led by BBH (12 / 20, score 74.90), HellaSwag (2 / 3, score 86.40), GSM8K (19 / 26, score 74). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

综合评估

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Off

75.20

54 / 64

BBH

Off

74.90

12 / 20

MMLU Pro

Off

56.54

99 / 115

数学推理

2 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Off

19 / 26

MATH

Off

42.30

38 / 42

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Off

62.60

22 / 28

HumanEval

Off

51.80

32 / 39

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

HellaSwag

Off

86.40

2 / 3

阅读理解

1 evaluations

Benchmark / mode

Score

Rank/total

DROP

Off

74.20

9 / 9

View benchmark analysis Compare with other models

Gemma2-27B

Model basics

Open source & experience

Official resources

API details

Benchmark Results

综合评估

数学推理

编程与软件工程

常识推理

阅读理解

Publisher

Model Overview

DataLearner 官方微信