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 Starling by Q-bert

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

  142   
  Autotrain compatible Base model:berkeley-nest/starl... Base model:merge:berkeley-nest... Base model:merge:q-bert/metama... Base model:q-bert/metamath-cyb...   Dataset:meta-math/metamathqa   En   Endpoints compatible   Math   Merge   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling 

MetaMath Cybertron Starling Benchmarks

ARC: 67.41 vs 96.7 (so35)-30.3%
HellaSwag: 86.26 vs 95.3 (gpt4)-9.5%
MMLU: 65.09 vs 88.3 (so35)-26.3%
TruthfulQA: 55.95 vs 59 (gpt4)-5.2%
WinoGrande: 81.29 vs 87.5 (gpt4)-7.1%
GSM8K: 71.49 vs 96.4 (so35)-25.8%
LLME Score: 0.17355
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MetaMath Cybertron Starling (Q-bert/MetaMath-Cybertron-Starling)

MetaMath Cybertron Starling Parameters and Internals

Model Type 
text-generation
Supported Languages 
en (high)
Input Output 
Input Format:
ChatML format
LLM NameMetaMath Cybertron Starling
Repository 🤗https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling 
Base Model(s)  MetaMath Cybertron   Starling LM 7B Alpha   Q-bert/MetaMath-Cybertron   berkeley-nest/Starling-LM-7B-alpha
Model Size7b
Required VRAM14.4 GB
Updated2025-01-05
MaintainerQ-bert
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the MetaMath Cybertron Starling

Model
Likes
Downloads
VRAM
...taMath Cybertron Starling GGUF0782 GB
...taMath Cybertron Starling GGUF121613 GB
...taMath Cybertron Starling GPTQ1224 GB
...etaMath Cybertron Starling AWQ1214 GB

Best Alternatives to MetaMath Cybertron Starling

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB27949
MegaBeam Mistral 7B 512K512K / 14.4 GB715947
SpydazWeb AI HumanAI RP512K / 14.4 GB281
SpydazWeb AI HumanAI 002512K / 14.4 GB201
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB319715
Hebrew Mistral 7B 200K256K / 30 GB274115
Astral 256K 7B V2250K / 14.4 GB170
Astral 256K 7B250K / 14.4 GB160
Boptruth Agatha 7B128K / 14.4 GB3270
Note: green Score (e.g. "73.2") means that the model is better than Q-bert/MetaMath-Cybertron-Starling.

Rank the MetaMath Cybertron Starling 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? 40868 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 v20241227
  Support LLM Explorer