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

LLaMA MoE V1 3 5B 2 8 by llama-moe

 »  All LLMs  »  llama-moe  »  LLaMA MoE V1 3 5B 2 8   URL Share it on

  90   
  Arxiv:2310.06694   Arxiv:2406.16554   Autotrain compatible   Custom code   En   Llama moe   Moe   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/llama-moe/LLaMA-MoE-v1-3_5B-2_8 

LLaMA MoE V1 3 5B 2 8 Benchmarks

LLME Score: 0.14282
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaMA MoE V1 3 5B 2 8 (llama-moe/LLaMA-MoE-v1-3_5B-2_8)

LLaMA MoE V1 3 5B 2 8 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, deployment
Limitations:
not fine-tuned for chatbot interactions
Additional Notes 
This model is a part of the LLaMA-MoE series which efficiently utilizes a Mixture-of-Experts (MoE) approach.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
SlimPajama
Data Volume:
200B tokens
Methodology:
Mixture-of-Experts; continual pre-training; partitioning LLaMA FFNs into experts
Model Architecture:
Mixture-of-Experts with LLaMA base
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
LLM NameLLaMA MoE V1 3 5B 2 8
Repository 🤗https://huggingface.co/llama-moe/LLaMA-MoE-v1-3_5B-2_8 
Model Size5b
Required VRAM13.5 GB
Updated2025-06-01
Maintainerllama-moe
Model Typellama_moe
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaMoEForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to LLaMA MoE V1 3 5B 2 8

Best Alternatives
Context / RAM
Downloads
Likes
LLaMA MoE V1 3 5B 4 164K / 13.5 GB13415
Note: green Score (e.g. "73.2") means that the model is better than llama-moe/LLaMA-MoE-v1-3_5B-2_8.

Rank the LLaMA MoE V1 3 5B 2 8 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? 47770 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