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.
 
 
 
 
 
 
sa_ddam213 3e252c81f6 LLamaContextParams epsilon and tensor split changes 2 years ago
..
GgmlInitParams.cs feat: support loading and saving state. 3 years ago
LLamaContextParams.cs LLamaContextParams epsilon and tensor split changes 2 years ago
LLamaFtype.cs feat: update quantize native params. 3 years ago
LLamaModelQuantizeParams.cs Various minor XML docs fixes 2 years ago
LLamaTokenData.cs refactor: LLamaModel and LLamaExecutor. 3 years ago
LLamaTokenDataArray.cs refactor: LLamaModel and LLamaExecutor. 3 years ago
NativeApi.Quantize.cs Various minor XML docs fixes 2 years ago
NativeApi.Sampling.cs feat: add chat session for refactored code. 3 years ago
NativeApi.cs Added model `Tokenize` method 2 years ago
NativeInfo.cs feat: add the framework and basic usages. 3 years ago
SafeLLamaContextHandle.cs Updated to use the new loading system in llama (llama_state). This new system has split model weights and contexts into two separate things, allowing one set of weights to be shared between many contexts. 2 years ago
SafeLLamaHandleBase.cs - Fixed null check 2 years ago
SafeLlamaModelHandle.cs Added comments on two properties 2 years ago
SamplingApi.cs refactor: some parts of code of LLamaModel. 3 years ago

C#/.NET上易用的LLM高性能推理框架,支持LLaMA和LLaVA系列模型。

C# Text Metal JavaScript HTML+Razor other