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 Sft by llama-moe

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

  20   
  Arxiv:2406.16554   Autotrain compatible   Custom code   En   Llama moe   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft 

LLaMA MoE V1 3 5B 2 8 Sft Benchmarks

LLME Score: 0.1677
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 Sft (llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft)

LLaMA MoE V1 3 5B 2 8 Sft Parameters and Internals

Model Type 
Mixture-of-Experts, Text Generation
Use Cases 
Areas:
Research, Commercial applications
Additional Notes 
This model is a supervised fine-tuned version specifically trained on the Deita-6k dataset for 2 epochs.
Supported Languages 
en (full proficiency)
Training Details 
Data Sources:
Deita-6k
Methodology:
Supervised fine-tuning
Model Architecture:
Mixture-of-Experts with Continual Pre-training
Input Output 
Input Format:
Text input
Accepted Modalities:
text
Output Format:
Text output
Performance Tips:
Use a GPU for model evaluation.
LLM NameLLaMA MoE V1 3 5B 2 8 Sft
Repository 🤗https://huggingface.co/llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft 
Model Size6.7b
Required VRAM13.5 GB
Updated2025-02-22
Maintainerllama-moe
Model Typellama_moe
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   3.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaMoEForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to LLaMA MoE V1 3 5B 2 8 Sft

Best Alternatives
Context / RAM
Downloads
Likes
LLaMA MoE V1 3 0B 2 16 Sft4K / 13.5 GB6451
LLaMA MoE V1 3 5B 4 16 Sft4K / 13.5 GB201
Note: green Score (e.g. "73.2") means that the model is better than llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft.

Rank the LLaMA MoE V1 3 5B 2 8 Sft 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