You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

StreamingTextDecoderTests.cs 1.4 kB

April 2024 Binary Update (#662) * Updated binaries, using [this build](https://github.com/SciSharp/LLamaSharp/actions/runs/8654672719/job/23733195669) for llama.cpp commit `f7001ccc5aa359fcf41bba19d1c99c3d25c9bcc7`. - Added all new functions. - Moved some functions (e.g. `SafeLlamaModelHandle` specific functions) into `SafeLlamaModelHandle.cs` - Exposed tokens on `SafeLlamaModelHandle` and `LLamaWeights` through a `Tokens` property. As new special tokens are added in the future they can be added here. - Changed all token properties to return nullable tokens, to handle some models not having some tokens. - Fixed `DefaultSamplingPipeline` to handle no newline token in some models. * Moved native methods to more specific locations. - Context specific things have been moved into `SafeLLamaContextHandle.cs` and made private - they're exposed through C# properties and methods already. - Checking that GPU layer count is zero if GPU offload is not supported. - Moved methods for creating default structs (`llama_model_quantize_default_params` and `llama_context_default_params`) into relevant structs. * Removed exception if `GpuLayerCount > 0` when GPU is not supported. * - Added low level wrapper methods for new per-sequence state load/save in `SafeLLamaContextHandle` - Added high level wrapper methods (save/load with `State` object or memory mapped file) in `LLamaContext` - Moved native methods for per-sequence state load/save into `SafeLLamaContextHandle` * Added update and defrag methods for KV cache in `SafeLLamaContextHandle` * Updated submodule to `f7001ccc5aa359fcf41bba19d1c99c3d25c9bcc7` * Passing the sequence ID when saving a single sequence state
1 year ago
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253
  1. using System.Text;
  2. using LLama.Common;
  3. using Xunit.Abstractions;
  4. namespace LLama.Unittest;
  5. public class StreamingTextDecoderTests
  6. : IDisposable
  7. {
  8. private readonly LLamaWeights _model;
  9. private readonly ITestOutputHelper _testOutputHelper;
  10. private readonly ModelParams _params;
  11. public StreamingTextDecoderTests(ITestOutputHelper testOutputHelper)
  12. {
  13. _testOutputHelper = testOutputHelper;
  14. _params = new ModelParams(Constants.GenerativeModelPath);
  15. _model = LLamaWeights.LoadFromFile(_params);
  16. }
  17. public void Dispose()
  18. {
  19. _model.Dispose();
  20. }
  21. [Fact]
  22. public void DecodesSimpleText()
  23. {
  24. var decoder = new StreamingTokenDecoder(Encoding.UTF8, _model);
  25. const string text = "The cat sat on the mat";
  26. var tokens = _model.NativeHandle.Tokenize(text, false, false, Encoding.UTF8);
  27. foreach (var lLamaToken in tokens)
  28. decoder.Add(lLamaToken);
  29. Assert.Equal(text, decoder.Read().Trim());
  30. }
  31. [Fact]
  32. public void DecodesComplexText()
  33. {
  34. var decoder = new StreamingTokenDecoder(Encoding.UTF8, _model);
  35. const string text = "猫坐在垫子上 😀🤨🤐😏";
  36. var tokens = _model.NativeHandle.Tokenize(text, false, false, Encoding.UTF8);
  37. foreach (var lLamaToken in tokens)
  38. decoder.Add(lLamaToken);
  39. Assert.Equal(text, decoder.Read().Trim());
  40. }
  41. }