.. |
Abstractions
|
Modified `ContextSize` in parameters to be nullable. A null value means autodetect from the model.
|
2023-11-07 19:41:44 +00:00 |
Common
|
Modified `ContextSize` in parameters to be nullable. A null value means autodetect from the model.
|
2023-11-07 19:41:44 +00:00 |
Exceptions
|
Assorted cleanup leftover after the huge change in the last PR (comments, syntax style, etc)
|
2023-10-19 00:26:30 +01:00 |
Extensions
|
Modified `ContextSize` in parameters to be nullable. A null value means autodetect from the model.
|
2023-11-07 19:41:44 +00:00 |
Grammars
|
Assorted cleanup leftover after the huge change in the last PR (comments, syntax style, etc)
|
2023-10-19 00:26:30 +01:00 |
Native
|
Modified `ContextSize` in parameters to be nullable. A null value means autodetect from the model.
|
2023-11-07 19:41:44 +00:00 |
runtimes
|
Added all binaries from this run: https://github.com/SciSharp/LLamaSharp/actions/runs/6762323560
|
2023-11-05 17:57:21 +01:00 |
AntipromptProcessor.cs
|
Added two new classes for detokenization tasks:
|
2023-10-23 00:33:50 +01:00 |
AssemblyAttributes.cs
|
- Created a higher level `Grammar` class which is immutable and contains a list of grammar rules. This is the main "entry point" to the grammar system.
|
2023-08-31 00:02:50 +01:00 |
ChatSession.cs
|
Improved method return description
|
2023-11-08 13:23:21 -06:00 |
GlobalSuppressions.cs
|
- Created a higher level `Grammar` class which is immutable and contains a list of grammar rules. This is the main "entry point" to the grammar system.
|
2023-08-31 00:02:50 +01:00 |
LLamaContext.cs
|
Fixed `Eval` on platforms < dotnet 5
|
2023-10-29 15:12:41 +00:00 |
LLamaEmbedder.cs
|
Added logging to embedder too
|
2023-10-19 21:09:44 +01:00 |
LLamaExecutorBase.cs
|
- Removed all `TokenToString` methods (it's never correct to use them, because sometimes one single character may be represented by multiple tokens).
|
2023-10-22 21:43:36 +01:00 |
LLamaInstructExecutor.cs
|
It works!
|
2023-10-28 21:32:21 +01:00 |
LLamaInteractExecutor.cs
|
It works!
|
2023-10-28 21:32:21 +01:00 |
LLamaQuantizer.cs
|
Assorted cleanup leftover after the huge change in the last PR (comments, syntax style, etc)
|
2023-10-19 00:26:30 +01:00 |
LLamaSharp.Runtime.targets
|
ggml-metal.metal MUST be copied to output folder
|
2023-09-10 20:42:15 +02:00 |
LLamaSharp.csproj
|
Add Microsoft.Extensions.Logging.Abstractions, update any required deps
|
2023-09-09 09:52:11 +12:00 |
LLamaStatelessExecutor.cs
|
Moved helper methods into `LLamaBatchSafeHandle`
|
2023-10-28 22:09:09 +01:00 |
LLamaTransforms.cs
|
- Improved coverage of `GBNFGrammarParser` up to 96%
|
2023-10-13 23:54:01 +01:00 |
LLamaWeights.cs
|
Reduced some uses of `NativeApi` in `BatchedDecoding` by adding some helper methods
|
2023-10-28 21:32:21 +01:00 |
StreamingTokenDecoder.cs
|
Fixed decoding of text "accumulating" over time (never properly clearing buffer)
|
2023-10-23 16:42:38 +01:00 |