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

Dart V1 Sft by p1atdev

 »  All LLMs  »  p1atdev  »  Dart V1 Sft   URL Share it on

  3469   
  Autotrain compatible Base model:p1atdev/dart-v1-bas... Base model:quantized:p1atdev/d...   Danbooru Dataset:isek-ai/danbooru-tags-...   Onnx   Opt   Optimum   Region:us   Safetensors   Sft   Trl
Model Card on HF 🤗: https://huggingface.co/p1atdev/dart-v1-sft 

Dart V1 Sft Benchmarks

LLME Score: 0.16675
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dart V1 Sft (p1atdev/dart-v1-sft)
🌟 Advertise your project 🚀

Dart V1 Sft Parameters and Internals

Model Type 
Causal language model
Use Cases 
Areas:
Research, Tag generation, Danbooru tag-specific applications
Applications:
Tag generation for images
Primary Use Cases:
Generating Danbooru tags for specified inputs.
Limitations:
Cannot accommodate flexible specifications.
Considerations:
Due to training with a specialized prompt format, natural language is not supported.
Supported Languages 
Danbooru tags (Primary supported input format)
Training Details 
Data Sources:
isek-ai/danbooru-tags-2023
Data Volume:
6M size of danbooru tags dataset
Methodology:
Trained using 🤗 transformers' trainer.
Hardware Used:
1x RTX 3070 Ti
Model Architecture:
OPT (Open Pretrained Transformer), but the position embeddings were not trained.
Input Output 
Input Format:
<|bos|> [RATING_PARENT], [RATING_CHILD] [COPYRIGHT, ...] [CHARACTER, ...] [LENGTH_TOKEN][GENERAL, ...]<|input_end|> [COMPLETION] <|eos|>
Accepted Modalities:
Danbooru tag sequences
Output Format:
Model completes tags in alphabetical order after [COMPLETION].
LLM NameDart V1 Sft
Repository 🤗https://huggingface.co/p1atdev/dart-v1-sft 
Base Model(s)  Dart V1 Base   p1atdev/dart-v1-base
Model Size138.9m
Required VRAM0.3 GB
Updated2025-09-15
Maintainerp1atdev
Model Typeopt
Model Files  0.3 GB
Model ArchitectureOPTForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.38.0
Tokenizer ClassDartTokenizer
Padding Token<|pad|>
Vocabulary Size67996
Torch Data Typebfloat16
Activation Functionrelu

Best Alternatives to Dart V1 Sft

Best Alternatives
Context / RAM
Downloads
Likes
Dart V1 Base2K / 0.3 GB66

Rank the Dart V1 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? 51387 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 v20241124
  Support LLM Explorer