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 Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  Qwen2.5 Math 7B Instruct Bnb 4bit   URL Share it on

  2191   
  Arxiv:2409.12122   4-bit   4bit   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-math-7...   Bitsandbytes   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-Math-7B-Instruct-bnb-4bit 

Qwen2.5 Math 7B Instruct Bnb 4bit Benchmarks

LLME Score: 0.27803
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 Math 7B Instruct Bnb 4bit (unsloth/Qwen2.5-Math-7B-Instruct-bnb-4bit)

Qwen2.5 Math 7B Instruct Bnb 4bit Parameters and Internals

Model Type 
Instruction-tuned, Mathematical, Chat Model
Use Cases 
Areas:
Research, Educational Tools
Primary Use Cases:
Solving mathematical problems in English and Chinese using CoT and TIR
Limitations:
Not recommended for tasks outside mathematical problem-solving
Additional Notes 
The model can be fine-tuned and optimized using Unsloth techniques which reduce memory usage by up to 70%.
Supported Languages 
English (proficient), Chinese (proficient)
Input Output 
Input Format:
Messages in JSON format with roles: system and user
Accepted Modalities:
Text
Output Format:
Text response
LLM NameQwen2.5 Math 7B Instruct Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen2.5-Math-7B-Instruct-bnb-4bit 
Base Model(s)  Qwen/Qwen2.5-Math-7B-Instruct   Qwen/Qwen2.5-Math-7B-Instruct
Model Size7b
Required VRAM5.5 GB
Updated2024-12-21
Maintainerunsloth
Model Typeqwen2
Instruction-BasedYes
Model Files  5.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 Math 7B Instruct Bnb 4bit

Model
Likes
Downloads
VRAM
...wen Math 7b 24 1 100 1 Nonmath030615 GB
...hemeng Qwen Math 7b 24 1 100 107015 GB

Best Alternatives to Qwen2.5 Math 7B Instruct Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct Bnb 4bit32K / 5.5 GB1649688
Qwen2.5 Coder 7B Instruct 4bit32K / 4.3 GB875352
Qwen UMLS 7B Instruct32K / 15.2 GB1017
Qwen2.5 7B Instruct 4bit32K / 4.3 GB108816
Novaeus Promptist 7B Instruct32K / 15.2 GB1408
FinancialAdvice Qwen2.5 7B32K / 15.2 GB331
...2.5 Coder 7B Instruct Bnb 4bit32K / 5.5 GB83234
Neumind Math 7B Instruct32K / 15.2 GB678
Math IIO 7B Instruct32K / 15.2 GB847
Qwen2.5 7B Instruct V1.232K / 15.2 GB4220
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-Math-7B-Instruct-bnb-4bit.

Rank the Qwen2.5 Math 7B Instruct Bnb 4bit 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? 40013 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 v20241217
  Support LLM Explorer