KarmaVLM Qwen1.5 0 5B by X-D-Lab

 ยป  All LLMs  ยป  X-D-Lab  ยป  KarmaVLM Qwen1.5 0 5B   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Llava qwen2   Region:us   Safetensors

KarmaVLM Qwen1.5 0 5B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
KarmaVLM Qwen1.5 0 5B (X-D-Lab/KarmaVLM-Qwen1.5-0_5B)
๐ŸŒŸ Advertise your project ๐Ÿš€

KarmaVLM Qwen1.5 0 5B Parameters and Internals

Model Type 
visual-question-answering, multimodal
Use Cases 
Primary Use Cases:
multi-round visual question answering, image comprehension
Additional Notes 
KarmaVLM supports multi-round conversations about images and is designed for high efficiency and strong image comprehension.
LLM NameKarmaVLM Qwen1.5 0 5B
Repository ๐Ÿค—https://huggingface.co/X-D-Lab/KarmaVLM-Qwen1.5-0_5B 
Model Size5b
Required VRAM1.9 GB
Updated2025-09-18
MaintainerX-D-Lab
Model Typellava_qwen2
Model Files  1.9 GB
Model ArchitectureLlavaQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|extra_0|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Rank the KarmaVLM Qwen1.5 0 5B 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? 51435 in total.

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