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 Instruct by Qwen

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

  284959   
  Arxiv:2309.00071   Autotrain compatible Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2-7b   Chat   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2-7B-Instruct 

Qwen2 7B Instruct Benchmarks

MMLU Pro: 31.64
GPQA: 6.38
MUSR: 7.37
BBH: 37.81
IFEval: 56.79 vs 88 (so35)-35.5%
MATH Lvl 5: 27.64
LLME Score: 0.41768
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 7B Instruct (Qwen/Qwen2-7B-Instruct)

Qwen2 7B Instruct Parameters and Internals

Model Type 
decoder, language model
Use Cases 
Areas:
research, text generation, multilingual processing, coding
Primary Use Cases:
language understanding, language generation, multilingual capability, coding, mathematics, reasoning
Considerations:
Ensure performance on shorter texts may be impacted when rope_scaling is configured for long texts.
Supported Languages 
en (English)
Training Details 
Data Volume:
large amount of data
Methodology:
supervised finetuning and direct preference optimization
Context Length:
131072
Model Architecture:
Transformer with SwiGLU activation, attention QKV bias, and group query attention
Input Output 
Accepted Modalities:
text
Performance Tips:
For handling long texts, enable YARN configuration in settings.
LLM NameQwen2 7B Instruct
Repository 🤗https://huggingface.co/Qwen/Qwen2-7B-Instruct 
Base Model(s)  Qwen2 7B   Qwen/Qwen2-7B
Model Size7b
Required VRAM15.4 GB
Updated2025-03-20
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
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 Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2 7B Instruct

Model
Likes
Downloads
VRAM
Qwen2 7B Instruct GGUF1117964091 GB
Qwen2 7B Instruct GPTQ Int42623565 GB
Qwen2 7B Instruct AWQ2112265 GB
Qwen2 7B Instruct GPTQ Int8172748 GB
Qwen2 7B Instruct GGUF03303 GB
Qwen2 7B Instruct GGUF11643 GB

Best Alternatives to Qwen2 7B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB335832273
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB422
Qwen2.5 7B RRP 1M986K / 15.2 GB1656
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB1417
Q2.5 Instruct 1M Harmony986K / 15.2 GB551
Impish QWEN 7B 1M986K / 15.2 GB834
COCO 7B Instruct 1M986K / 15.2 GB784
Apollo 7B986K / 15.2 GB510
Qwen2.5 7B Instruct 1M986K / 15.2 GB12752
Qwen2.5 7B Sky R1 Mini986K / 15.2 GB650
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B-Instruct.

Rank the Qwen2 7B Instruct 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? 45351 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