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.
1331 Commits
8 Branches
333 MB
304 Download
 
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
LLamaSharp/LLama
Martin Evans 3b0b2ab224
Merge pull request #721 from martindevans/kv_cache_view 		2 years ago
..
Abstractions fix: typos. 2 years ago
Batched Removed (marked as obsolete) prompting with a string for `Conversation`. Tokenization requires extra parameters (e.g. addBos, special) which require special considersation. For now it's better to tokenize using other tools and pass the tokens directly. 2 years ago
Common fix: typos. 2 years ago
Exceptions Swapped `StatelessExecutor` to use `llama_decode`! 2 years ago
Extensions fix: typos. 2 years ago
Grammars Code cleanup driven by R# suggestions: 2 years ago
Native Merge pull request #721 from martindevans/kv_cache_view 2 years ago
Sampling April 2024 Binary Update (#662) 2 years ago
runtimes April 2024 Binary Update (#662) 2 years ago
AntipromptProcessor.cs Make AntipromptProcessor public 2 years ago
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. 2 years ago
ChatSession.cs InitializeSessionFromHistoryAsync changed 2 years ago
GlobalSuppressions.cs Logging interceptor (#649) 2 years ago
LLamaContext.cs Add method to get BOS token. 2 years ago
LLamaEmbedder.cs - Added tests for generating embeddings with generative model and embedding model 2 years ago
LLamaExecutorBase.cs Refactor executors 2 years ago
LLamaInstructExecutor.cs Refactor executors 2 years ago
LLamaInteractExecutor.cs Refactor executors 2 years ago
LLamaQuantizer.cs Modified `llama_model_quantize` to accept argument by `ref` instead of pointer. 2 years ago
LLamaSharp.Runtime.targets fix: add cuda llava native libraries. 2 years ago
LLamaSharp.csproj release: update release info of packages. 2 years ago
LLamaStatelessExecutor.cs Refactor executors 2 years ago
LLamaTemplate.cs Split template out to a field, so it can be changed more easily. 2 years ago
LLamaTransforms.cs Add LLaMA3 chat session example. 2 years ago
LLamaWeights.cs Added optional `IProgress` parameter to `LoadFromFileAsync` 2 years ago
LLavaWeights.cs - Added `LoadFromFileAsync` method for `LLavaWeights` 2 years ago
StreamingTokenDecoder.cs Assorted small changes to clean up some code warnings 2 years ago
Usings.cs - Added `LLamaTemplate` which efficiently formats a series of messages according to the model template. 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