Add llama C++ example #926
+212
−11
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Empty file.
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| // Copyright (c) Microsoft Corporation. All rights reserved. | ||
| // Licensed under the MIT License. | ||
|
|
||
| #include <iostream> | ||
| #include <string> | ||
| #include "ort_genai.h" | ||
|
|
||
| // C++ API Example | ||
|
|
||
| void CXX_API(const char* model_path) { | ||
| std::cout << "Creating model..." << std::endl; | ||
| auto model = OgaModel::Create(model_path); | ||
| std::cout << "Creating tokenizer..." << std::endl; | ||
| auto tokenizer = OgaTokenizer::Create(*model); | ||
| auto tokenizer_stream = OgaTokenizerStream::Create(*tokenizer); | ||
|
|
||
| while (true) { | ||
| std::string text; | ||
| std::cout << "Prompt: " << std::endl; | ||
| std::getline(std::cin, text); | ||
|
|
||
| const std::string prompt = "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\nYou are a helpful AI assistant. Give a short answer to the following<|eot_id|><|start_header_id|>user<|end_header_id|>" + text + "<|eot_id|><|start_header_id|>assistant<|end_header_id|>"; | ||
|
|
||
| auto sequences = OgaSequences::Create(); | ||
| tokenizer->Encode(prompt.c_str(), *sequences); | ||
|
|
||
| std::cout << "Generating response..." << std::endl; | ||
| auto params = OgaGeneratorParams::Create(*model); | ||
| params->SetSearchOption("max_length", 1024); | ||
| params->SetSearchOptionBool("do_sample", true); | ||
| params->SetInputSequences(*sequences); | ||
|
|
||
| auto generator = OgaGenerator::Create(*model, *params); | ||
|
|
||
| while (!generator->IsDone()) { | ||
| generator->ComputeLogits(); | ||
| generator->GenerateNextToken(); | ||
|
|
||
| // Show usage of GetOutput | ||
| std::unique_ptr<OgaTensor> output_logits = generator->GetOutput("logits"); | ||
|
There was a problem hiding this comment. Is the There was a problem hiding this comment. So |
||
|
|
||
| // Assuming output_logits.Type() is float as it's logits | ||
|
There was a problem hiding this comment. Just fyi, the raw model output can be float16 if the model runs on cuda. Our internal "processed logits" are always float32 There was a problem hiding this comment. So is this correct, or not? |
||
| // Assuming shape is 1 dimensional with shape[0] being the size | ||
| auto logits = reinterpret_cast<float*>(output_logits->Data()); | ||
|
|
||
| // Print out the logits using the following snippet, if needed | ||
| //auto shape = output_logits->Shape(); | ||
| //for (size_t i=0; i < shape[0]; i++) | ||
| // std::cout << logits[i] << " "; | ||
| //std::cout << std::endl; | ||
|
|
||
| const auto num_tokens = generator->GetSequenceCount(0); | ||
| const auto new_token = generator->GetSequenceData(0)[num_tokens - 1]; | ||
| std::cout << tokenizer_stream->Decode(new_token) << std::flush; | ||
| } | ||
|
|
||
| for (int i = 0; i < 3; ++i) | ||
| std::cout << std::endl; | ||
| } | ||
| } | ||
|
|
||
|
|
||
| static void print_usage(int /*argc*/, char** argv) { | ||
| std::cerr << "usage: " << argv[0] << " model_path" << std::endl; | ||
| } | ||
|
|
||
| int main(int argc, char** argv) { | ||
| if (argc != 2) { | ||
| print_usage(argc, argv); | ||
| return -1; | ||
| } | ||
|
|
||
| // Responsible for cleaning up the library during shutdown | ||
| OgaHandle handle; | ||
|
|
||
| std::cout << "-------------" << std::endl; | ||
| std::cout << "Run Llama" << std::endl; | ||
| std::cout << "-------------" << std::endl; | ||
|
|
||
| #ifdef USE_CXX | ||
|
There was a problem hiding this comment. What is the USE_CXX here for, given the whole file is C++? |
||
| std::cout << "C++ API" << std::endl; | ||
| CXX_API(argv[1]); | ||
| #endif | ||
|
|
||
| return 0; | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could we have something like the following?
The abbreviations and names can be different, but the idea would be to create examples grouped by input and output modality.
LLMcould be for decoder-only models (e.g. LLaMA, Phi)VLMcould be for vision-text models (e.g. Phi-3/Phi-3.5 vision)ALMcould be for audio-text models (e.g. Whisper)There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think this is a great proposal for a new PR!