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

MetaMath Cybertron by Q-bert

 »  All LLMs  »  Q-bert  »  MetaMath Cybertron   URL Share it on

  63   
  Autotrain compatible Base model:fblgit/una-cybertro... Base model:finetune:fblgit/una...   Dataset:meta-math/metamathqa   En   Endpoints compatible   Math   Mistral   Region:us   Safetensors   Sharded   Tensorflow

MetaMath Cybertron Benchmarks

ARC: 66.47 vs 96.7 (so35)-31.3%
HellaSwag: 85.54 vs 95.3 (gpt4)-10.2%
MMLU: 63.71 vs 88.3 (so35)-27.8%
TruthfulQA: 57.71 vs 59 (gpt4)-2.2%
WinoGrande: 79.64 vs 87.5 (gpt4)-9%
GSM8K: 70.51 vs 96.4 (so35)-26.9%
LLME Score: 0.18047
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

MetaMath Cybertron Parameters and Internals

LLM NameMetaMath Cybertron
Repository 🤗https://huggingface.co/Q-bert/MetaMath-Cybertron 
Base Model(s)  Una Cybertron 7B V2 Bf16   MetaMath Mistral 7B   fblgit/una-cybertron-7b-v2-bf16   meta-math/MetaMath-Mistral-7B
Model Size7b
Required VRAM14.4 GB
Updated2024-10-18
MaintainerQ-bert
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16
MetaMath Cybertron (Q-bert/MetaMath-Cybertron)

Best Alternatives to MetaMath Cybertron

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB21756
MegaBeam Mistral 7B 512K512K / 14.4 GB252641
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB106115
Hebrew Mistral 7B 200K256K / 30 GB267715
Astral 256K 7B V2250K / 14.4 GB80
Astral 256K 7B250K / 14.4 GB80
Boptruth Agatha 7B128K / 14.4 GB6080
Buddhi 128K Chat 7B128K / 14.4 GB130115
Test001128K / 14.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than Q-bert/MetaMath-Cybertron.

Rank the MetaMath Cybertron 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? 36966 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 v2024072803
  Support LLM Explorer