📝 LM-Kit.NET Change History
📅 Version 2024.11.4 (18 November 2024)
New Features
- Added Vulkan backend for Linux
- Improved compatibility with macOS ARM and macOS x64
- Enhanced CPU inference speed
- Added support for .NET 9
📅 Version 2024.11.3 (12 November 2024)
New Features
- Added
CreateGrammarFromStringList
method to theGrammar
class - Added
WhitelistedValues
property to theTextExtractionElementFormat
class
📅 Version 2024.11.2 (05 November 2024)
New Features
- Added overloads to
GetEmbeddings
andGetEmbeddingsAsync
methods in theEmbedder
class to support batch processing of multiple inputs.
📅 Version 2024.11.1 (04 November 2024)
New Features
- Added support for Granit models
- Added
Perplexity
property to theBeforeTokenSamplingEventArgs
class - Added
Perplexity
property to theAfterTokenSamplingEventArgs
class - Added
ContinueLastAssistantResponse
andContinueLastAssistantResponseAsync
methods to theMultiTurnConversation
class
Improvements
- Optimized dynamic sampling mechanisms.
📅 Version 2024.10.5 (24 October 2024)
New Features
- Added the
GeneratedTokens
property to theChatHistory.Message
class. - Added the
TerminationReason
property to theChatHistory.Message
class. - Introduced the
TextExtractionElementFormat
class. - Introduced the
TextExtractionElementFormat.TextCaseMode
enumeration. - Added the
TextExtractionElementFormat
property to theTextExtractionElement
class.
Improvements
- Enhanced structured text extraction.
- Added new formatting options to text extraction elements.
- Improved function calling capabilities.
- Refined JSON data sampling.
- Optimized dynamic sampling mechanisms.
📅 Version 2024.10.4 (17 October 2024)
Improvements
- Structured text extraction improvements
- Function calling improvements
- Refined JSON data sampling.
- Optimized dynamic sampling mechanisms.
📅 Version 2024.10.3 (16 October 2024)
New Features
- Added
TextExtraction
class - Added
TextExtractionResult
class - Added
TextExtractionResultElement
class - Added
ElementType
enumeration - Added
DateTime
parameter type support to function calling
Improvements
- Optimized dynamic sampling mechanisms.
📅 Version 2024.10.2 (09 October 2024)
New Features
- Added
TextExtractionElement
class - Added
CreateJsonGrammarFromExtractionElements(IEnumerable<TextExtractionElement> extractionElements)
method overload to theGrammar
class
Improvements
- Optimized dynamic sampling mechanisms.
📅 Version 2024.10.1 (01 October 2024)
New Features
- Added
CreateTrainingObject
method overload to theEmotionDetection
class - Added
GetTrainingData
method to theEmotionDetection
class - Introduced
EmotionDetection.TrainingDataset
enumeration - Introduced
JsonNumArray
,JsonIntArray
andJsonStringArray
members to theLMKit.Data.Json.JsonBasicType
enumeration - Introduced
TextTranslation.TrainingDataset
enumeration - Added
GetTrainingData
method to theTextTranslation
class - Added
EnableDynamicSampling
property to theConfiguration
class
Improvements
- Improvements to generic classification accuracy and speed
- Improved global performance with Llama 3.2 models
- Improved global performance with Qwen 2.5 models
- Fine-tuning: extended compatibility to all Llama architectures
- Improved sampling of JSON array structures
📅 Version 2024.9.4 (25 September 2024)
New Features
- Added support for array parameters in function calls
- Added
ForceFunctionSelection
property to theSingleFunctionCall
class - Introduced
LMKit2024_09_INT
member to theSentimentAnalysis.TrainingDataset
enumeration
Improvements
- Improved function calling accuracy and speed
- Improved emotion detection engine accuracy and speed
- Strong improvements to generic classification accuracy and speed
- Improved accuracy of the language detection engine
Bug Fixes
- Fixed an memory leak in the fine-tuning engine
📅 Version 2024.9.3 (18 September 2024)
Improvements
- Improved function calling accuracy
- Enhanced language detection accuracy
- Boosted generic classification accuracy and speed
- Increased inference speed on CPU
📅 Version 2024.9.2 (11 September 2024)
New Features
- Added
Seed
property toRandomSampling
,MirostatSampling
, andMirostat2Sampling
classes - Introduced
TrimAuto
member to theInputLengthOverflowPolicy
enumeration - Enabled deserialization of
ChatHistory
objects without specifying aModel
parameter
Improvements
- Further increased inference speed on CPU
- Enhanced internal API for better error handling
📅 Version 2024.9.1 (6 September 2024)
Improvements
- Optimized inference speed on CPU
- Implemented checks to prevent access to disposed objects
- Improved exception handling in quantization features
📅 Version 2024.9.0 (3 September 2024)
New Features
- Added
GetToken
method to theVocabulary
class - Introduced
Confidence
property to theTextTranslation
class - Added
MaximumInputTokens
property to theSingleTurnConversation
class
Improvements
- Enhanced JSON content sampling strategy
- Extended CUDA backend compatibility across more Windows configurations
- Improved accuracy of the language detection engine
- Enhanced compatibility with MAUI
📅 Version 2024.8.4 - Preview (26 August 2024)
New Features
- Introduced
GlobalConfiguration
static class
Improvements
- Refined JSON content sampling strategy
- Improved function calling accuracy and speed
- Increased inference speed with Gemma2 models
- Enhanced classification accuracy with tiny-small models
Bug Fixes
- Fixed an issue when computing embeddings from a token array matching the context size
📅 Version 2024.8.3 - Preview (21 August 2024)
Improvements
- Improved support for Phi 3.5 models
📅 Version 2024.8.2 - Preview (20 August 2024)
New Features
- Added
CreateJsonGrammarFromJsonScheme
method to theGrammar
class
Improvements
- Improved JSON content sampling strategy
- Enhanced function calling accuracy and speed
📅 Version 2024.8.1 - Preview (15 August 2024)
New Features
- Added Vulkan backend 🔥
- Introduced
FunctionCallResult
property to theFunctionCallEventArgs
class - Added
EnableVulkan
property to theRuntime
class - Included
KeepLast
property in theAfterTokenSamplingEventArgs
class
Improvements
- Refined JSON content sampling strategy
- Enhanced function calling accuracy and speed
📅 Version 2024.8.0 - Preview (8 August 2024)
New Features
- Added
CreateJsonGrammarFromFields
method to theGrammar
class - Enabled function calling support with any model class 🔥
- Introduced
SingleFunctionCall
andFunctionCallResult
classes - Added
LMFunctionAttribute
attribute
Improvements
- Enhanced grammar sampling strategy, especially for JSON schemes
📅 Version 2024.7.10 - Preview (6 August 2024)
New Features
- Added support for Google Gemma 2 2B models 🔥
- Introduced
CreateJsonGrammarFromTextFields
method to theGrammar
class
Improvements
- Improved grammar sampling strategy, particularly with JSON schemes
📅 Version 2024.7.9 - Preview (31 July 2024)
New Features
- Added
Version
property to theRuntime
class
Bug Fixes
- Fixed an issue enabling neutral emotion support in the
EmotionDetection
class - Resolved issues when running fine-tuning with gradient checkpointing
📅 Version 2024.7.8 - Preview (30 July 2024)
New Features
- Added
MaximumContextLength
property to theSingleTurnConversation
class
Improvements
- Enhanced inference engine handling of context overflow scenarios
📅 Version 2024.7.7 - Preview (29 July 2024)
Improvements
- Enhanced compatibility with .NET Framework 4.6.2
Bug Fixes
- Resolved a crash related to grammar sampling
📅 Version 2024.7.6 - Preview (27 July 2024)
New Features
- Added support for LLaMA 3.1 models 🔥
Improvements
- Enhanced logging mechanism
🎉 Version 2024.7.1 - Preview (23 July 2024)
🎉🥳 Initial release! 🥳🎉
😺 🐱 🐾