ShareCaptioner by stanrom

 ยป  All LLMs  ยป  stanrom  ยป  ShareCaptioner   URL Share it on

  Arxiv:2311.12793   Custom code   Feature-extraction   Internlmxcomposer   Pytorch   Region:us   Sharded
Model Card on HF ๐Ÿค—: https://huggingface.co/stanrom/ShareCaptioner 

ShareCaptioner Benchmarks

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

ShareCaptioner Parameters and Internals

Model Type 
captioner, vision-assisted
Use Cases 
Areas:
computer vision, natural language processing, machine learning, artificial intelligence
Primary Use Cases:
producing high-quality image captions
Training Details 
Data Sources:
ShareGPT4V detailed caption data
Data Volume:
100K GPT4-Vision-generated image-text pairs
Methodology:
fine-tuned with a resolution of 448x448
LLM NameShareCaptioner
Repository ๐Ÿค—https://huggingface.co/stanrom/ShareCaptioner 
Required VRAM16.8 GB
Updated2025-02-22
Maintainerstanrom
Model TypeInternLMXComposer
Model Files  10.0 GB: 1-of-2   6.8 GB: 2-of-2
Model ArchitectureInternLMXComposerForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.33.1
Is Biased1
Tokenizer ClassInternLMXComposerTokenizer
Padding Token</s>
Vocabulary Size103172
Torch Data Typebfloat16

Best Alternatives to ShareCaptioner

Best Alternatives
Context / RAM
Downloads
Likes
ShareCaptioner2K / 16.8 GB32955

Rank the ShareCaptioner Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227