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

Dart V2 MoE Base by p1atdev

 »  All LLMs  »  p1atdev  »  Dart V2 MoE Base   URL Share it on

  160   
  Autotrain compatible   Danbooru Dataset:isek-ai/danbooru-tags-...   Mixtral   Moe   Optimum   Region:us   Safetensors   Sft   Trl
Model Card on HF 🤗: https://huggingface.co/p1atdev/dart-v2-moe-base 

Dart V2 MoE Base Benchmarks

LLME Score: 0.18914
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dart V2 MoE Base (p1atdev/dart-v2-moe-base)

Dart V2 MoE Base Parameters and Internals

Model Type 
Causal language model
Additional Notes 
This model is primarily designed for generating Danbooru tags using Danbooru tags dataset from 2005 to 2024. Moreover, the model includes various variants tailored for specific tasks like SFT and pretraining.
Supported Languages 
Danbooru tags (high)
Training Details 
Data Sources:
isek-ai/danbooru-tags-2024
Data Volume:
7M size of danbooru tags dataset
Hardware Used:
8x RTX A6000
Model Architecture:
Mixtral
Input Output 
Input Format:
<|bos|>{copyright_tags_here}{character_tags_here}<|rating:general|><|aspect_ratio:tall|><|length:long|>{general_tags_here}
Accepted Modalities:
text
Output Format:
Danbooru tags separated by commas
LLM NameDart V2 MoE Base
Repository 🤗https://huggingface.co/p1atdev/dart-v2-moe-base 
Model Size165.7m
Required VRAM0.3 GB
Updated2025-02-22
Maintainerp1atdev
Model Typemixtral
Model Files  0.3 GB
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length1024
Model Max Length1024
Transformers Version4.38.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size30649
Torch Data Typebfloat16

Best Alternatives to Dart V2 MoE Base

Best Alternatives
Context / RAM
Downloads
Likes
Dart V2 MoE Sft1K / 0.3 GB9799
Note: green Score (e.g. "73.2") means that the model is better than p1atdev/dart-v2-moe-base.

Rank the Dart V2 MoE Base 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