Nicholai/jan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: Add FAQs content

Browse Source
This commit is contained in:
Arista Indrajaya 2024-03-07 18:25:08 +07:00
parent 751c273cde
commit 7d988cc2d9
1 changed files with 77 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
docs/docs/guides/faq.mdx
View File

@ -17,6 +17,80 @@ keywords:
]
---
:::caution
This is currently under development.
:::
## General Issues
- **Why can't I download models like Pandora 11B Q4 and Solar Instruct 10.7B Q4?**
- These models might have been removed or taken down. Please check the [Pre-configured Models](models-list.mdx) for the latest updates on model availability.
- **Why does Jan display "Apologies, something's amiss" when I try to run it?**
- This issue may arise if you're using an older Intel chip that does not fully support AVX instructions required for running AI models. Upgrading your hardware may resolve this issue.
- **How can I use Jan in Russia?**
- To use Jan in Russia, a VPN or [HTTPS - Proxy](./advanced-settings/http-proxy.mdx) is recommended to bypass any regional restrictions that might be in place.
- **I'm experiencing an error on startup from Nitro. What should I do?**
- If you encounter errors with Nitro, try switching the path to use the Nitro executable for the version 12-0. This adjustment can help resolve path-related issues.
## Download and Installation Issues
- **What does "Error occurred: Unexpected token" mean?**
- This error usually indicates a problem with your internet connection or that your access to certain resources is being blocked. Using a VPN or [HTTPS - Proxy](./advanced-settings/http-proxy.mdx) can help avoid these issues by providing a secure and unrestricted internet connection.
- **Why aren't my downloads working?**
- If you're having trouble downloading directly through Jan, you might want to download the model separately and then import it into Jan. Detailed instructions are available on [here](install.mdx).
- **Jan AI doesn't open on my Mac with an Intel processor. What can I do?**
- Granting the `.npm` folder permission for the user can resolve issues related to permissions on macOS, especially for users with Intel processors.
- **What should I do if the model download freezes?**
- If a model download freezes, consider importing the models manually. You can find more detailed guidance on how to do this at [Manual Import](./models/import-models.mdx) article.
- **I received a message that the model GPT4 does not exist or I do not have access. What should I do?**
- This message typically means you need to top up your credit with OpenAI or check your access permissions for the model.
- **I can't download models from "Explore the Hub." What's the solution?**
- Uninstalling Jan, clearing the cache, and reinstalling it following the guide provided [here](install.mdx) may help. Also, consider downloading the `.gguf` model via a browser as an alternative approach.
## Technical Issues and Solutions
- **How can I download models with a socks5 proxy or import a local model file?**
- Nightly builds of Jan offer support for downloading models with socks5 proxies or importing local model files.
- **My device shows no GPU usage and lacks a Settings folder. What should I do?**
- Using the nightly builds of Jan can address issues related to GPU usage and the absence of a Settings folder, as these builds contain the latest fixes and features.
- **Why does Jan display a toast message saying a model is loaded when it is not actually loaded?**
- This issue can be resolved by downloading the `.gguf` file from Hugging Face and replacing it in the model folder. This ensures the correct model is loaded.
- **How to enable CORS when running Nitro?**
- By default, CORS (Cross-Origin Resource Sharing) is disabled when running Nitro. Enabling CORS can be necessary for certain operations and integrations. Check the official documentation for instructions on how to enable CORS if your workflow requires it.
## Compatibility and Support
- **How to use GPU AMD for Jan?**
- Jan now supports AMD GPUs through Vulkan. This enhancement allows users with AMD graphics cards to leverage GPU acceleration, improving performance for AI model computations.
- **Is Jan available for Android or iOS?**
- Jan is primarily focused on the Desktop app and does not currently offer mobile apps for Android or iOS. The development team is concentrating on enhancing the desktop experience.
## Development and Features
- **Can I use local files from my computer with Jan?**
- The feature to use local files is currently in development. For more information, please our offical [Discord](https://discord.com/invite/FTk2MvZwJH) for the latest update.
- **Does Jan support Safetensors?**
- At the moment, Jan only supports GGUF. However, there are plans to support `.safetensor` files in the future.
- **I hope to customize the installation path of each model. Is that possible?**
- Yes you can customize the installation path. Please see [here](https://github.com/janhq/jan/issues/1010) for more information.
## Troubleshooting
- **What should I do if there's high CPU usage while Jan is idle?**
- If you notice high CPU usage while Jan is idle, consider using the nightly builds of Jan
- **What does the error "Failed to fetch" mean, and how can I fix it?**
- The "Failed to fetch" error typically occurs due to network issues or restrictions. Using the nightly builds of Jan may help overcome these issues by providing updated fixes and features.
- **What should I do if "Failed to fetch" occurs using MacBook Pro with Intel HD Graphics 4000 1536 MB?**
- Ensure that the model size is less than 90% of your available VRAM and that the VRAM is accessible to the app. Managing the resources effectively can help mitigate this issue.