taeyeonlee

@Hzfengsy I'll ask to Qualcomm for the info.

Hi @bhushan23 According to the python code (https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/_shared/llama/), I coded the c++ code in Android App using NDK and pytorch libs. For example, after running llama_v2_7b_chat_quantized_TokenGenerator_2_Quantized.bin, there're 513 outputs from...

Hi @bhushan23 In Android App (C++), PromptProcessor_1 (llama_v2_7b_chat_quantized_PromptProcessor_1_Quantized.bin) has the third input (ie. input[2], called as position_ids_cos) which has the tensor shape [1, 1, 1024, 64], and it's data type...

> Hi there, I am working on this too, I don't think you are using the right backend , you should try the HTP backend instead Hi @dirtdust , How...

@bhushan23 I downloaded the source model (LLaMA-2-7b) from https://huggingface.co/meta-llama/Llama-2-7b-hf/tree/main, according to the tutorial (file:///C:/Qualcomm/AIStack/QAIRT/2.25.0.240728/docs/Genie/general/tutorials.html). and then it was converted (./qnn-genai-transformer-composer --quantize Z4 --outfile /home/taeyeon/QAI_Genie/llama_qct_genie.bin --model /home/taeyeon/QAI_Genie/Llama-2-7b-hf --export_tokenizer_json). How to calibrate...

hi, @bhushan23 Could you please share the plan to release the Android sample app with C++ APIs ?

@bhushan23 QnnSampleApp::createFromBinary() is called as like below. ``` std::vector models = {app->MODEL_TokenGenerator_1, app->MODEL_TokenGenerator_2, app->MODEL_TokenGenerator_3, app->MODEL_TokenGenerator_4}; if (sample_app::StatusCode::SUCCESS != app->createFromBinary(models)) { ``` The QnnSampleApp.cpp is modified as below. ``` sample_app::StatusCode sample_app::QnnSampleApp::createFromBinary(std::vector...

@superjackie @langchain4j Any solution for Android Platform ? I faced the same issue : Android App (Java) stops when calling EmbeddingModel embeddingModel = new BgeSmallEnV15QuantizedEmbeddingModel(); Caused by: java.io.IOException: Resource not...

Hi @Harrison-niu The LD_LIBRARY_PATH and ADSP_LIBRARY_PATH are already set. but it failed to run. DId you succeed to run it on S24 ?

Hi @kuaashish The repo is read-only, I can't raise the issue on the community repo. The community repo says that Unity App can use the mediapipe AAR using wrapper AAR....