Jagle VL 2.2B Jagle + FineVision
Jagle VL 2.2B Jagle + 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 mixture combines Jagle and FineVision. The card declares Apache 2.0 and separately notes terms for proprietary-model outputs included in FineVision.Jagle VL 2.2B Jagle + FineVision official model card
Compare the dataset choice at fixed architecture
Practical guidance. Compare the combined model with both single-dataset variants. A mixed-data result helps assess transfer, but does not isolate which dataset caused a change.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | Jagle-VL-2.2B-Jagle-FineVision |
| Language ancestry | Qwen3-1.7B.Jagle VL 2.2B Jagle + FineVision official model card |
| Vision ancestry | Google SigLIP 2 So400m, patch16 at 512 pixels.Jagle VL 2.2B Jagle + FineVision official model card |
| Training dataset | Jagle + FineVision.Jagle VL 2.2B Jagle + 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