Comments (1)
Hello, thank you for reporting this issue in the LocalAI repository. I'm a bot, an experiment of @mudler, designed to help audit the tickets opened here.
Based on the information provided, we understand that you are experiencing an issue with the curl
command on your Mac when attempting to load a model using the LocalAI version 2.12.4 in Docker AMD64 emulation. You've noticed that using escaped double quotes instead of single quotes does not work on your Mac, while it does work on Ubuntu (WSL), as well as Windows cmd & PowerShell with different argument names, all against the same Windows WSL Docker with GPU & CUDA 12.
The error you're encountering is: {"error":{"code":500,"message":"could not load model: rpc error: code = Unavailable desc = error reading from server: EOF","type":""}}
. Meanwhile, Docker on PC displays successful loading of the model, and Docker on Mac shows a different model being loaded.
To help better investigate this issue, please provide the following information:
- Is there any specific reason you are using escaped double quotes instead of single quotes when running the
curl
command? - Are there any other command-line differences between your Mac and other environments that could potentially impact this process?
- Have you attempted reinstalling LocalAI or Docker on your Mac?
- Do you have any logs to share while running LocalAI in debug mode (
--debug
orDEBUG=true
)? This may help in understanding the problem better.
By providing these additional details, we'll be better equipped to assist you in resolving this issue. Please remember to avoid using any tool or external services to maintain the integrity of the audit process.
from localai.
Related Issues (20)
- limit models to api keys HOT 1
- After several exchanges, llama-cpp hangs up and no longer returns any response. HOT 7
- Very difficult to use, there are a lot of bugs HOT 2
- llama-cpp CPU 1500%,Very slow...What to do? HOT 1
- tts coqui xtts_v2 not working without speaker_idx HOT 2
- ERROR [api builder 3/12] COPY .git . HOT 2
- LOCALAI_LOG_LEVEL seemingly does nothing HOT 3
- I would like the --tensor-parallel-size setting of the vllm backend to be added to yaml. HOT 1
- lamma3 8B and 70B gguf support? Can support function calling? HOT 2
- transport: Error while dialing: dial tcp 127.0.0.1:40825: connect: connection refused HOT 4
- [SSE] The chat completion chunk object from the /chat/completions API endpoint contains a single character instead of a complete token HOT 2
- Fine grained authentication system HOT 4
- All-in-One (AIO) Image - Models are not loading due to "grpc service not ready" HOT 3
- txt2vid requires opencv + memory attn. HOT 6
- [Feature Request] - GPT-Researcher HOT 2
- missing nvidia-smi disable gpu support HOT 5
- [question,documentation]How to load API keys list from json file? HOT 2
- Embeddings with langchain fail: "rpc error: code = Unavailable desc = error reading from server: EOF" HOT 2
- AIO - memory issue - embedding HOT 4
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 localai.