Qwen/Qwen2-7B-Instruct cover image

Qwen/Qwen2-7B-Instruct

The 7 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.

The 7 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.

Public
$0.07 / Mtoken
bfloat16
32k
Function
ProjectLicense
Qwen/Qwen2-7B-Instruct cover image

Qwen2 7b

Ask me anything

0.00s

Qwen2-7B-Instruct

Introduction

Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 7B Qwen2 model.

Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.

Qwen2-7B-Instruct supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs. Please refer to this section for detailed instructions on how to deploy Qwen2 for handling long texts.

For more details, please refer to our blog, GitHub, and Documentation.

Model Details

Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.

Training details

We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.

Evaluation

We briefly compare Qwen2-7B-Instruct with similar-sized instruction-tuned LLMs, including Qwen1.5-7B-Chat. The results are shown below:

DatasetsLlama-3-8B-InstructYi-1.5-9B-ChatGLM-4-9B-ChatQwen1.5-7B-ChatQwen2-7B-Instruct
English
MMLU68.469.572.459.570.5
MMLU-Pro41.0--29.144.1
GPQA34.2--27.825.3
TheroemQA23.0--14.125.3
MT-Bench8.058.208.357.608.41
Coding
Humaneval62.266.571.846.379.9
MBPP67.9--48.967.2
MultiPL-E48.5--27.259.1
Evalplus60.9--44.870.3
LiveCodeBench17.3--6.026.6
Mathematics
GSM8K79.684.879.660.382.3
MATH30.047.750.623.249.6
Chinese
C-Eval45.9-75.667.377.2
AlignBench6.206.907.016.207.21