scisharp
/
LLamaSharp
Not watched
1
0
Fork 0
Code
Releases 17 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
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.
182 Commits
8 Branches
333 MB
147 Download
 
 
 
 
 
 
Tree: fe3bd11dfa
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'fe3bd11dfa'
${ noResults }
LLamaSharp/LLama
Martin Evans fe3bd11dfa
Merge branch 'master' into master 		2 years ago
..
Abstractions Various minor XML docs fixes 2 years ago
Common Merge branch 'master' into master 2 years ago
Exceptions Various minor XML docs fixes 2 years ago
Extensions - Removed the `Update` and `GetOrDefault` extension methods (they were unused). 2 years ago
Native Update llama.cpp binaries to 5f631c2 and align the context to that version 2 years ago
OldVersion Merge pull request #68 from martindevans/sampling_improvements 2 years ago
runtimes Update llama.cpp binaries to 5f631c2 and align the context to that version 2 years ago
ChatSession.cs Various minor XML docs fixes 2 years ago
LLamaEmbedder.cs Fixed multiple cases where an `IEnumerable<T>` was enumerated multiple times. 2 years ago
LLamaExecutorBase.cs Correctly passing through mu value to mirostate instead of resetting it every time. 2 years ago
LLamaInstructExecutor.cs Correctly passing through mu value to mirostate instead of resetting it every time. 2 years ago
LLamaInteractExecutor.cs Correctly passing through mu value to mirostate instead of resetting it every time. 2 years ago
LLamaModel.cs Update llama.cpp binaries to 5f631c2 and align the context to that version 2 years ago
LLamaQuantizer.cs Various minor XML docs fixes 2 years ago
LLamaSharp.Runtime.targets Libraries with MacOS Metal Support 2 years ago
LLamaSharp.csproj fix breaking change in llama.cpp; bind to latest version llama.cpp to support new quantization method 2 years ago
LLamaStatelessExecutor.cs Correctly passing through mu value to mirostate instead of resetting it every time. 2 years ago
LLamaTransforms.cs Merge branch 'master' into more_multi_enumeration_fixes 2 years ago
ResettableLLamaModel.cs Implemented a new `LlamaModel.State` handle which internally stores the state as natively allocated memory. This allows it to exceed the 2GB limit on C# arrays. 2 years ago
Utils.cs Update llama.cpp binaries to 5f631c2 and align the context to that version 2 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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