license: other
license_name: aplux-model-farm
license_link: >-
https://huggingface.co/APLUX-Agora/InternVL3-2B-Instruct/blob/main/LICENSE_MODEL_FARM.pdf
pipeline_tag: image-text-to-text
tags:
- Agora
- QNN
- AIoT
- Qualcomm
InternVL3-2B-Instruct model resources
InternVL3-2B-Instruct，来自 Model Farm 官方预览目录，逐板卡验证后开放运行。
Board builds that Agora runs and measures on real Qualcomm boards. Try it online, without a board: https://mega.aidlux.com/models/internvl3-2b-instruct
| SoC · board | Precisions | Measured on Agora (default precision) |
|---|---|---|
| QCS8550 · 犀牛派 X1 (Rhino Pi X1) | W4A16 | 36.1 tokens/s |
Task: 视觉语言模型. Inputs: image (image), text (text). Outputs: text (text).
Download
export AGORA_WORKSPACE="$HOME/my-internvl3-2b-instruct"
export AGORA_SOC='QCS8550'
hf download APLUX-Agora/InternVL3-2B-Instruct \
--include "targets/$AGORA_SOC/*" --local-dir "$AGORA_WORKSPACE/resources"
Each targets/<SoC>/ holds model.json (default precision and variant paths) and one directory per precision. Context binaries are named model.bin; multi-file packages are kept as published by Model Farm.
Pre- and post-processing, the runner and an exported project: open the model on Agora and choose “部署指南”, or export any workflow that uses it.
Licence and provenance
Source model licence: see the original model's terms. Converted, deployable resources: APLUX Model Farm License (LICENSE_MODEL_FARM.pdf). See NOTICE.md and SHA256SUMS.