Uform Gen by unum-cloud

 ยป  All LLMs  ยป  unum-cloud  ยป  Uform Gen   URL Share it on

  Autotrain compatible Base model:finetune:unum-cloud... Base model:unum-cloud/uform-vl... Dataset:christophschuhmann/ms ...   Dataset:huggingfacem4/vqav2   Dataset:sbu captions   Dataset:visual genome   En   Endpoints compatible   Image-captioning   Image-to-text   Region:us   Safetensors   Sharded   Tensorflow   Visual-question-answering   Vlm
Model Card on HF ๐Ÿค—: https://huggingface.co/unum-cloud/uform-gen 

Uform Gen Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Uform Gen (unum-cloud/uform-gen)
๐ŸŒŸ Advertise your project ๐Ÿš€

Uform Gen Parameters and Internals

Model Type 
Image Captioning, Visual Question Answering
Additional Notes 
Can generate image captions and answer questions about images. Utilizes prompts for precise behavior control.
Supported Languages 
en ()
Training Details 
Data Sources:
MSCOCO, SBU Captions, Visual Genome, VQAv2, GQA
Input Output 
Input Format:
PIL Image
Accepted Modalities:
text, image
Output Format:
Text
Performance Tips:
Uses float16 on compatible GPUs for best performance.
LLM NameUform Gen
Repository ๐Ÿค—https://huggingface.co/unum-cloud/uform-gen 
Base Model(s)  Uform Vl English   unum-cloud/uform-vl-english
Model Size1.5b
Required VRAM6 GB
Updated2025-08-18
Maintainerunum-cloud
Model Typevlm
Model Files  5.0 GB: 1-of-2   1.0 GB: 2-of-2
Supported Languagesen
Model ArchitectureVLMForCausalLM
Licenseapache-2.0
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Torch Data Typefloat32

Best Alternatives to Uform Gen

Best Alternatives
Context / RAM
Downloads
Likes
Uform Gen Chat0K / 6 GB14018
Note: green Score (e.g. "73.2") means that the model is better than unum-cloud/uform-gen.

Rank the Uform Gen 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? 50729 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124