LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen2 7B by Qwen

 »  All LLMs  »  Qwen  »  Qwen2 7B   URL Share it on

  60595   
  Autotrain compatible   Conversational   En   Endpoints compatible   Pretrained   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2-7B 

Qwen2 7B Benchmarks

MMLU Pro: 35.37
GPQA: 7.27
MUSR: 14.32
BBH: 34.71
IFEval: 31.49 vs 88 (so35)-64.2%
ARC: 59.73 vs 96.7 (so35)-38.2%
HellaSwag: 79.82 vs 95.3 (gpt4)-16.2%
MMLU: 70.45 vs 88.3 (so35)-20.2%
TruthfulQA: 53.14 vs 59 (gpt4)-9.9%
WinoGrande: 74.35 vs 87.5 (gpt4)-15%
GSM8K: 72.93 vs 96.4 (so35)-24.3%
MATH Lvl 5: 20.39
LLME Score: 0.36075
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 7B (Qwen/Qwen2-7B)

Qwen2 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
Language understanding, language generation, multilingual capability, coding, mathematics, reasoning
Supported Languages 
English (proficient), Chinese (proficient), Multilingual (varied proficiency)
Training Details 
Methodology:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention.
Model Architecture:
Transformer
Input Output 
Accepted Modalities:
text
Performance Tips:
It is suggested to not use base language models for text generation directly. Instead, apply post-training techniques like SFT, RLHF, continued pretraining on this model.
LLM NameQwen2 7B
Repository 🤗https://huggingface.co/Qwen/Qwen2-7B 
Model Size7b
Required VRAM15.4 GB
Updated2025-03-12
MaintainerQwen
Model Typeqwen2
Model Files  4.0 GB: 1-of-4   3.9 GB: 2-of-4   3.9 GB: 3-of-4   3.6 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2 7B

Model
Likes
Downloads
VRAM
...lphin 2.9.2 Qwen2 7B Bpw6 EXL21116 GB
Samantha Qwen2 7B AWQ0105 GB

Best Alternatives to Qwen2 7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB332966262
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB352
Qwen2.5 7B MixStock V0.1986K / 15.2 GB1653
Hush Qwen2.5 7B V1.1986K / 15.2 GB261
Hush Qwen2.5 7B V1.3986K / 15.2 GB192
Hush Qwen2.5 7B V1.4986K / 15.2 GB231
Hush Qwen2.5 7B V1.2986K / 15.2 GB211
Hush Qwen2.5 7B Preview986K / 15.2 GB840
Qwen2.5 7B Preview986K / 15.2 GB130
Qwen2.5 7B RRP 1M986K / 15.2 GB2086
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B.

Rank the Qwen2 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 44887 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer