Comments (4)
Can you post the full stack trace of the error? Thanks.
from llamasharp.
System.ArgumentException
HResult=0x80070057
Message=EmbeddingMode must be true (Parameter 'params')
Source=LLamaSharp
StackTrace:
at LLama.LLamaEmbedder..ctor(LLamaWeights weights, IContextParams params, ILogger logger)
at EGOIST.ViewModels.Pages.TextViewModel.<GenerationSwitchModels>b__52_0() in E:\Native\Projects\EGOIST\EGOIST\ViewModels\Pages\TextViewModel.cs:line 266
at System.Threading.ExecutionContext.RunInternal(ExecutionContext executionContext, ContextCallback callback, Object state)
--- End of stack trace from previous location ---
at System.Threading.ExecutionContext.RunInternal(ExecutionContext executionContext, ContextCallback callback, Object state)
I figured it out. It seems that when I use GenerationModelEmbedder = new(GenerationModel, GenerationModelParameters);, it requires EmbeddingMode = true in GenerationModelParameters. This wasn't necessary in previous versions. Sorry, I'm not very familiar with Visual Studio and detailed stack traces yet.
side question, how to use OpenCL backend ? I have a AMD RX580 GPU but even after installing OpenCL backend it still running on CPU
from llamasharp.
One of the changes in 0.10.0 was that the LLamaEmbedder
requires EmbeddingMode = true
set. previously it would modify your config to set it, which wouldn't always be what you wanted (e.g. if the config is shared, that might get enabled without you realising it). Sounds like you've bumped into that.
how to use OpenCL backend
I'm not sure of the status, but I don't think OpenCL is available for LLamaSharp yet. Some initial work was done to add CLBLAST in 0.10.0, but (as far as I know) it's not shipped to nuget yet.
from llamasharp.
Since you'vce figured out the problem I'll close this issue :)
from llamasharp.
Related Issues (20)
- Nuget references both CPU and CUDA simultaneously HOT 2
- Thread Safety in llama.cpp HOT 1
- Llama.web app published into iis windows 64bit server, after deployment model values not loaded from appsettings HOT 4
- Not able to read fields from appsetings.json HOT 4
- Examples don't run with CUDA12 HOT 17
- Consider adding Windows on ARM build of llama.dll to LLamaSharp.Backend.Cpu HOT 7
- Drastic CUDA compute speed drop in last version HOT 13
- Build CUDA with AVX HOT 2
- Fatal error. System.Runtime.InteropServices.SEHException HOT 32
- Godot game engine example HOT 25
- how to prevent the llama from completing requests HOT 1
- about NVidia GPU use example HOT 4
- SemanticKernel ChatCompletion is Stateless HOT 5
- Segmentation fault on Docker HOT 2
- [LLamaSharp.Backend.Cuda12 v0.10.0] Unable to load the model onto multiple GPUs HOT 3
- Unable to use lora in llamasharp but can use it in llama.cpp HOT 8
- AMD GPUs Support
- Exception error when sending any prompts. HOT 7
- Parallel Inferencing? HOT 28
- Information on new important updates in llama.cpp HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llamasharp.