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

MetaMath 13B V1.0 by meta-math

 »  All LLMs  »  meta-math  »  MetaMath 13B V1.0   URL Share it on

  1022   

MetaMath 13B V1.0 is an open-source language model by meta-math. Features: 13b LLM, VRAM: 52.1GB, Context: 4K, License: llama2, HF Score: 52.7, LLM Explorer Score: 0.13, Arc: 49.5, HellaSwag: 76.5, MMLU: 47.7, TruthfulQA: 41.6, WinoGrande: 72.5, GSM8K: 28.5.

  Arxiv:2309.12284   Dataset:meta-math/metamathqa   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/meta-math/MetaMath-13B-V1.0 

MetaMath 13B V1.0 Benchmarks

ARC: 49.49 vs 96.7 (so35)-48.8%
HellaSwag: 76.48 vs 95.3 (gpt4)-19.7%
MMLU: 47.74 vs 88.3 (so35)-45.9%
TruthfulQA: 41.58 vs 59 (gpt4)-29.5%
WinoGrande: 72.45 vs 87.5 (gpt4)-17.2%
GSM8K: 28.51 vs 96.4 (so35)-70.4%
LLME Score: 0.13379
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MetaMath 13B V1.0 (meta-math/MetaMath-13B-V1.0)
🌟 Advertise your project 🚀

MetaMath 13B V1.0 Parameters and Internals

Model Type 
Text generation
Use Cases 
Areas:
Research, Education
Applications:
Mathematical question answering
Primary Use Cases:
Mathematical problem-solving, Question generation
Additional Notes 
Boosts MATH performance by changing the base model to Llemma-7B.
Supported Languages 
English (Proficient)
Training Details 
Data Sources:
MetaMathQA
Methodology:
Fine-tuning on MetaMathQA datasets
Input Output 
Input Format:
instructional prompts
Accepted Modalities:
text
Output Format:
textual responses
Performance Tips:
Use 'Let's think step by step' to guide responses
LLM NameMetaMath 13B V1.0
Repository 🤗https://huggingface.co/meta-math/MetaMath-13B-V1.0 
Model Size13b
Required VRAM52.1 GB
Updated2026-03-29
Maintainermeta-math
Model Typellama
Model Files  10.0 GB: 1-of-6   9.9 GB: 2-of-6   9.9 GB: 3-of-6   9.9 GB: 4-of-6   9.9 GB: 5-of-6   2.5 GB: 6-of-6
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat32

Quantized Models of the MetaMath 13B V1.0

Model
Likes
Downloads
VRAM
MetaMath 13B V1.0 GGUF3635 GB
MetaMath 13B V1.0 GPTQ1187 GB
MetaMath 13B V1.0 AWQ197 GB

Best Alternatives to MetaMath 13B V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB50
Yarn Llama 2 13B 128K128K / 26 GB300112
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB50
LongAlign 13B 64K64K / 26 GB1713
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB523
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB64
Openbuddy Llama2 13b64k V1564K / 26.1 GB52
Note: green Score (e.g. "73.2") means that the model is better than meta-math/MetaMath-13B-V1.0.

Rank the MetaMath 13B V1.0 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? 52394 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer