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

Octopus V4 by NexaAIDev

 »  All LLMs  »  NexaAIDev  »  Octopus V4   URL Share it on

  240   
  Arxiv:2404.19296   Ai agent   Autotrain compatible   Conversational   Custom code   En   Graph   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Octopus V4 Benchmarks

LLME Score: 0.25773
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Octopus V4 Parameters and Internals

LLM NameOctopus V4
Repository 🤗https://huggingface.co/NexaAIDev/Octopus-v4 
Base Model(s)  microsoft/Phi-3   microsoft/Phi-3
Model Size3.8b
Required VRAM7.7 GB
Updated2024-09-13
MaintainerNexaAIDev
Model Typephi3
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensecc-by-nc-4.0
Context Length131072
Model Max Length131072
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16
Octopus V4 (NexaAIDev/Octopus-v4)

Best Alternatives to Octopus V4

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB322524461
Phi 3 Mini 128K Instruct128K / 7.7 GB1829751567
Phi 3.5 Mini ITA128K / 7.7 GB44458
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB5728
....5 Mini 3.8B ArliAI RPMax V1.1128K / 7.7 GB605
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB2025
Phi 3.5 Mini Sonet RP128K / 15.4 GB250
Phi 3.5 Mini ChatML128K / 7.7 GB200
MedPhi 3 Mini V1128K / 7.7 GB19422
SeaPhi3 Mini128K / 7.7 GB38994
Note: green Score (e.g. "73.2") means that the model is better than NexaAIDev/Octopus-v4.

Rank the Octopus V4 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? 35941 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