OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF
image-text-to-text model by OpenGVLab
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.
[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggingface.co/papers/2411.10442) [\[📜 InternVL3\]](https://huggingface.co/papers/2504.10479) [\[📜 InternVL3.5\]](https://huggingface.co/papers/2508.18265) [\[🆕 Blog\]](https://internvl.github.io/blog/) [\[🗨️ Chat Demo\]](https://chat.intern-ai.org.cn/) [\[🚀 Quick Start\]](#quick-start) [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/) We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\%…
Read the full model card ↗ · Preview checked 2026-10-06T06:40:03.544Z
Inside the original model card — Document outline
- InternVL35-GPT-OSS-20B-A4B-Preview
- Introduction
- InternVL3.5 Family
- Github Format
- HuggingFace Format
- Model Architecture
- Training and Deployment Strategy
- Pre-Training
- Supervised Fine-Tuning
- Cascade Reinforcement Learning
- Visual Consistency Learning
- Test-Time Scaling
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
OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF is a image-text-to-text model repository published by OpenGVLab 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)
- 629,247
- Cumulative likes
- 9
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 21,232,768,704
- Architecture
- InternVLForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2025-08-29T13:16:54.000Z
- Last modified
- 2025-09-08T09:54:41.000Z
Compatibility and lineage
Reported languages: multilingual
Reported base models: OpenGVLab/InternViT-300M-448px-V2_5, openai/gpt-oss-20b
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 2026-10-06T06:39:58.556Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.