llava-hf/llava-onevision-qwen2-0.5b-ov-hf
image-text-to-text model by llava-hf
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: [](https://colab.research.google.com/drive/1-4AtYjR8UMtCALV0AswU1kiNkWCLTALT?usp=sharing) Below is the model card of 0.5B LLaVA-Onevision model which is copied from the original LLaVA-Onevision model card that you can find here. Model type: LLaVA-Onevision is an open-source multimodal LLM trained by fine-tuning Qwen2 on GPT-generated multimodal instruction-following data. LLaVA-OneVision is the first single model that can simultaneously push the performance boundaries of open LMMs in three important computer vision scenarios: single-image, multi-image, and video scenarios. Importantly, the design of LLaVA-OneVision allows strong transfer learning across different modalities/scenarios, yielding new emerging capabilities. In particular, strong video understanding and cross-scenario capabilities are demonstrated through task transfer from images to videos. Model date: LLaVA-Onevision-0.5-ov was added in August 2024. Paper or resources for more information: https://llava-vl.github.io/ First, make sure to have transformers installed from branch or transformers >= 4.45.0. The model supports multi-image and…
Read the full model card ↗ · Preview checked 2026-11-01T19:48:56.279Z
Inside the original model card — Document outline
- LLaVA-Onevision Model Card
- Model details
- How to use the model
- Using pipeline:
- Using pure transformers:
- Model optimization
- 4-bit quantization through bitsandbytes library
- Use Flash-Attention 2 to further speed-up generation
- Usage w/ Transformers.js
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
llava-hf/llava-onevision-qwen2-0.5b-ov-hf is a image-text-to-text model repository published by llava-hf on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 623,782
- Cumulative likes
- 60
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 893,675,552
- Architecture
- LlavaOnevisionForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2024-08-13T08:28:18.000Z
- Last modified
- 2025-06-18T13:57:09.000Z
Compatibility and lineage
Reported languages: en, zh
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-30T06:39:14.347Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.