MathCoder2 DeepSeekMath 7B by MathGenie

 »  All LLMs  »  MathGenie  »  MathCoder2 DeepSeekMath 7B   URL Share it on

  Arxiv:2410.08196 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Dataset:mathgenie/mathcode-pil...   En   Llama   Math   Region:us   Safetensors   Sharded   Tensorflow

MathCoder2 DeepSeekMath 7B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MathCoder2 DeepSeekMath 7B (MathGenie/MathCoder2-DeepSeekMath-7B)

MathCoder2 DeepSeekMath 7B Parameters and Internals

Model Type 
text-generation
Additional Notes 
The MathCoder2 models are trained using the MathCode-Pile dataset which is designed to improve mathematical reasoning capabilities.
Supported Languages 
en (primary)
LLM NameMathCoder2 DeepSeekMath 7B
Repository 🤗https://huggingface.co/MathGenie/MathCoder2-DeepSeekMath-7B 
Base Model(s)  Deepseek Math 7B Base   deepseek-ai/deepseek-math-7b-base
Model Size7b
Required VRAM13.9 GB
Updated2025-02-08
MaintainerMathGenie
Model Typellama
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   3.9 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.43.2
Tokenizer ClassLlamaTokenizer
Padding Token<|end▁of▁sentence|>
Vocabulary Size102400
Torch Data Typebfloat16

Best Alternatives to MathCoder2 DeepSeekMath 7B

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB491
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB50542
LlamaStock 8B128K / 16.1 GB171
SuperNeuralDreadDevil 8B128K / 16.1 GB351
Yarn Llama 2 7B 128K128K / 13.5 GB595239
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB83
LLaMA 7B PoSE Linear 96K96K / 27 GB82
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB91
Chat Llama2 7B 80K80K / 13.8 GB90
Llama2 7B 80K80K / 13.8 GB90
Note: green Score (e.g. "73.2") means that the model is better than MathGenie/MathCoder2-DeepSeekMath-7B.

Rank the MathCoder2 DeepSeekMath 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? 42807 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227