Jagle VL 2.2B FineVision
Jagle VL 2.2B FineVision combines Qwen3-1.7B with SigLIP 2 So400m and a two-layer projector. It is an LLM-jp-trained multimodal derivative.
Research release
The dataset defines this release
The training corpus is FineVision. The card declares Apache 2.0 for the model and also instructs users to comply with terms attached to proprietary-model outputs in the dataset.Jagle VL 2.2B FineVision official model card
Compare the dataset choice at fixed architecture
Practical guidance. Use this English-dataset variant as a control for the Japanese Jagle mixture. It does not establish that Japanese content was covered to the same extent.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | Jagle-VL-2.2B-FineVision |
| Language ancestry | Qwen3-1.7B.Jagle VL 2.2B FineVision official model card |
| Vision ancestry | Google SigLIP 2 So400m, patch16 at 512 pixels.Jagle VL 2.2B FineVision official model card |
| Training dataset | FineVision.Jagle VL 2.2B FineVision official model card |
Related models
- Jagle VL 2.2B Jagle
LLM-jp / NII LLMC · Jagle VL
The 2.2B Jagle vision-language experiment trained with Jagle data.
Launch date not confirmedResearch releaseDownloadable - LLM-jp-4 VL 9B
LLM-jp / NII LLMC · LLM-jp-4 VL
A Japanese-English vision-language reasoning model that changes both the language backbone and training data from the beta.
Launch date not confirmedResearch releaseDownloadable