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

Qwen2.5 Math 7B Instruct by Qwen

 »  All LLMs  »  Qwen  »  Qwen2.5 Math 7B Instruct   URL Share it on

  28606   
  Arxiv:2409.12122   Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-math-7...   Chat   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct 

Qwen2.5 Math 7B Instruct Benchmarks

MMLU Pro: 20.22
GPQA: 1.57
MUSR: 2.89
BBH: 21.49
IFEval: 26.36 vs 88 (so35)-70%
MATH Lvl 5: 58.08
LLME Score: 0.33726
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Qwen2.5 Math 7B Instruct Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Education
Applications:
Mathematics Problem Solving
Primary Use Cases:
Mathematical question answering, Mathematics-based chat
Limitations:
> Mainly supports solving English and Chinese math problems, Does not recommend for other tasks
Considerations:
Focus on CoT and TIR for problem-solving
Additional Notes 
Qwen2.5-Math series supports both Chain-of-Thought (CoT) and Tool-Integrated Reasoning (TIR) for mathematical problem-solving.
Supported Languages 
en (Fluent), zh (Fluent)
Release Notes 
Version:
1.0
Date:
August 2024
Notes:
Initial release of Qwen2.5-Math-7B-Instruct with enhanced capability in solving math problems using CoT and TIR.
LLM NameQwen2.5 Math 7B Instruct
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct 
Base Model(s)  Qwen/Qwen2.5-Math-7B   Qwen/Qwen2.5-Math-7B
Model Size7b
Required VRAM15.4 GB
Updated2025-06-09
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 Length4096
Model Max Length4096
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace
Qwen2.5 Math 7B Instruct (Qwen/Qwen2.5-Math-7B-Instruct)

Quantized Models of the Qwen2.5 Math 7B Instruct

Model
Likes
Downloads
VRAM
...n2.5 Math 7B Instruct Bnb 4bit424875 GB

Best Alternatives to Qwen2.5 Math 7B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB1204830329
Qwen2.5 7B RRP 1M986K / 15.2 GB4476
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB142
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB137
Q2.5 Instruct 1M Harmony986K / 15.2 GB152
Impish QWEN 7B 1M986K / 15.2 GB214
COCO 7B Instruct 1M986K / 15.2 GB174
Apollo 7B986K / 15.2 GB120
Qwen2.5 7B Instruct 1M986K / 15.2 GB8732
Qwen2.5 7B Sky R1 Mini986K / 15.2 GB120
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-Math-7B-Instruct.

Rank the Qwen2.5 Math 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? 48023 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 v20241124
  Support LLM Explorer