Qwen2-VL-2B-rkllm

.gitattributes

@@ -49,3 +49,10 @@ models/Qwen2-VL-2B-Instruct/onnx/vision_encoder_bnb4.onnx_data filter=lfs diff=l
 models/Qwen2-VL-2B-Instruct/onnx/vision_encoder_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
 models/Qwen2-VL-2B-Instruct-ONNX-Q4-F16/onnx/QwenVL_A.onnx.data filter=lfs diff=lfs merge=lfs -text
 models/Qwen2-VL-2B-Instruct-ONNX-Q4-F16/onnx/QwenVL_E.onnx.data filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/demo filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/demo.jpg filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/imgenc filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/lib/librkllmrt.so filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/lib/librknnrt.so filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/qwen2_vl_2b_vision_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
+models/Qwen2-VL-2B-rkllm/Qwen2-VL-2B-Instruct.rkllm filter=lfs diff=lfs merge=lfs -text

models/Qwen2-VL-2B-rkllm/.gitattributes

@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL-2B-Instruct.rkllm filter=lfs diff=lfs merge=lfs -text
+demo_Linux_aarch64/demo filter=lfs diff=lfs merge=lfs -text
+demo_Linux_aarch64/imgenc filter=lfs diff=lfs merge=lfs -text
+demo_Linux_aarch64/lib/librkllmrt.so filter=lfs diff=lfs merge=lfs -text
+demo_Linux_aarch64/lib/librknnrt.so filter=lfs diff=lfs merge=lfs -text
+qwen2_vl_2b_vision_rk3588.rknn filter=lfs diff=lfs merge=lfs -text

models/Qwen2-VL-2B-rkllm/Qwen2-VL-2B-Instruct.rkllm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d476c790768f6b1d9041604bb3205cc299f186cbcb06d81941661797d12df5b0
+size 2035398748

models/Qwen2-VL-2B-rkllm/README.md

@@ -0,0 +1,95 @@
+---
+base_model:
+- Qwen/Qwen2-VL-2B
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- rknn
+- rkllm
+- chat
+- vision
+- rk3588
+- multimodal
+---
+## 3ib0n's RKLLM Guide
+These models and binaries require an RK3588 board running rknpu driver version 0.9.7 or above
+
+## Steps to reproduce conversion
+```shell
+# Download and setup miniforge3
+curl -L -O "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
+bash Miniforge3-$(uname)-$(uname -m).sh
+
+# activate the base environment
+source ~/miniforge3/bin/activate
+
+# create and activate a python 3.8 environment
+conda create -n rknn-llm-1.1.4 python=3.8
+conda activate rknn-llm-1.1.4
+
+# clone the lastest rknn-llm toolkit
+git clone https://github.com/airockchip/rknn-llm.git
+
+# update the following 4 files to your desired models and output locations
+cd rknn-llm/examples/rkllm_multimodal_demo
+nano export/export_vision.py # update model path and output path
+nano export/export_vision_rknn.py # update model path 
+nano export/export_rkllm.py # update input and output paths 
+nano data/make_input_embeds_for_quantize.py # update model path
+
+# intstall necessary dependencies for the above 
+pip install transformers accelerate torchvision rknn-toolkit2==2.2.1
+pip install --upgrade torch pillow # necessary to use vision models with opset_version=18
+
+# export vision models and create input embeddings
+cd export/
+python export_vision.py 
+python export_vision_rknn.py
+cd ..
+python data/make_input_embeds_for_quantize.py 
+
+# install rkllm and export the language model
+pip install ../../rkllm-toolkit/packages/rkllm_toolkit-1.1.4-cp38-cp38-linux_x86_64.whl
+python export/export_rkllm.py 
+```
+
+## Steps to build and run demo
+
+```shell
+# Dwonload the correct toolchain for working with rkllm
+# Documentation here: https://github.com/airockchip/rknn-llm/blob/main/doc/Rockchip_RKLLM_SDK_EN_1.1.0.pdf
+wget https://developer.arm.com/-/media/Files/downloads/gnu-a/10.2-2020.11/binrel/gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu.tar.xz
+tar -xz gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu.tar.xz
+
+# ensure that the gcc compiler path is set to the location where the toolchain dowloaded earlier is unpacked
+nano deploy/build-linux.sh # update the gcc compiler path
+
+# compile the demo app
+cd delpoy/
+./build-linux.sh 
+```
+
+## Steps to run the app
+More information and original guide: https://github.com/airockchip/rknn-llm/tree/main/examples/rkllm_multimodel_demo
+```shell
+# push install dir to device
+adb push ./install/demo_Linux_aarch64 /data
+# push model file to device
+adb push qwen2_vl_2b_vision_rk3588.rknn /data/models
+adb push Qwen2-VL-2B-Instruct.rkllm /data/models
+# push demo image to device
+adb push ../data/demo.jpg /data/demo_Linux_aarch64
+
+adb shell
+cd /data/demo_Linux_aarch64
+# export lib path
+export LD_LIBRARY_PATH=./lib
+# soft link models dir
+ln -s /data/models .
+# run imgenc
+./imgenc models/qwen2_vl_2b_vision_rk3588.rknn demo.jpg
+# run llm(Pure Text Example)
+./llm models/Qwen2-VL-2B-Instruct.rkllm 128 512
+# run demo(Multimodal Example)
+./demo demo.jpg models/qwen2_vl_2b_vision_rk3588.rknn models/Qwen2-VL-2B-Instruct.rkllm 128 512
+```

models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/demo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7141948b3a63038d86efee9c4a81d60ce21cfdacbae4c7964169c9277a18755b
+size 6853536

models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/imgenc

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8264cfe228be63b2a1e0f66a5ed39d6405354d7342a71d76beb3e1c7ab04bab6
+size 6857520

models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/lib/librkllmrt.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cef353105c3bfd31f99c4963fce8498d2fac633d845633c904f523b7c3bcd0a
+size 6239192

models/Qwen2-VL-2B-rkllm/demo_Linux_aarch64/lib/librknnrt.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1170e5f99f2db7ed4d3a4c2bdbed941b7363bd090e0c28b4e210f40614327911
+size 7192616

models/Qwen2-VL-2B-rkllm/qwen2_vl_2b_vision.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c90ff2336c9b2d79936af93ca61c0ad2bb0de6f534ad23884ac0d883c809a9
+size 1196568

models/Qwen2-VL-2B-rkllm/qwen2_vl_2b_vision_rk3588.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec311f2cc37c3926aa64ace5ead7d4809641fcadf8cb063c2f5ceb33dea5aab7
+size 1391014138

models/Qwen2-VL-2B-rkllm/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/3ib0n/Qwen2-VL-2B-rkllm