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

Llama 3 70Bx2 MoE by cloudyu

 »  All LLMs  »  cloudyu  »  Llama 3 70Bx2 MoE   URL Share it on

  19   
  Autotrain compatible   Conversational   Endpoints compatible   Instruct   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cloudyu/Llama-3-70Bx2-MOE 

Llama 3 70Bx2 MoE Benchmarks

MMLU Pro: 46.02
GPQA: 19.13
MUSR: 20.85
BBH: 51.42
IFEval: 54.82 vs 88 (so35)-37.7%
MATH Lvl 5: 21.75
LLME Score: 0.28938
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 70Bx2 MoE (cloudyu/Llama-3-70Bx2-MOE)

Llama 3 70Bx2 MoE Parameters and Internals

Model Type 
text-generation
LLM NameLlama 3 70Bx2 MoE
Repository 🤗https://huggingface.co/cloudyu/Llama-3-70Bx2-MOE 
Model Size126.9b
Required VRAM229.4 GB
Updated2025-02-22
Maintainercloudyu
Model Typemixtral
Instruction-BasedYes
Model Files  4.8 GB: 1-of-52   4.8 GB: 2-of-52   5.0 GB: 3-of-52   4.8 GB: 4-of-52   4.8 GB: 5-of-52   5.0 GB: 6-of-52   4.8 GB: 7-of-52   5.0 GB: 8-of-52   4.8 GB: 9-of-52   5.0 GB: 10-of-52   4.8 GB: 11-of-52   4.8 GB: 12-of-52   5.0 GB: 13-of-52   4.8 GB: 14-of-52   5.0 GB: 15-of-52   4.8 GB: 16-of-52   5.0 GB: 17-of-52   4.8 GB: 18-of-52   4.8 GB: 19-of-52   5.0 GB: 20-of-52   4.8 GB: 21-of-52   5.0 GB: 22-of-52   4.8 GB: 23-of-52   5.0 GB: 24-of-52   4.8 GB: 25-of-52   4.8 GB: 26-of-52   5.0 GB: 27-of-52   4.8 GB: 28-of-52   5.0 GB: 29-of-52   4.8 GB: 30-of-52   5.0 GB: 31-of-52   4.8 GB: 32-of-52   4.8 GB: 33-of-52   5.0 GB: 34-of-52   4.8 GB: 35-of-52   5.0 GB: 36-of-52   4.8 GB: 37-of-52   5.0 GB: 38-of-52   4.8 GB: 39-of-52   4.8 GB: 40-of-52   5.0 GB: 41-of-52   4.8 GB: 42-of-52   5.0 GB: 43-of-52   4.8 GB: 44-of-52   5.0 GB: 45-of-52   4.8 GB: 46-of-52   4.8 GB: 47-of-52
Model ArchitectureMixtralForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Vocabulary Size128256
Torch Data Typebfloat16

Rank the Llama 3 70Bx2 MoE 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? 43470 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