Originally created by @DraculaVladimir on GitHub (Jun 10, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/2987
# Bug Report
## Description
Custom Model not loading instructions when loading through "@"
**Bug Summary:**
Custom Model not loading instructions when loading through "@"
**Steps to Reproduce:**
Load any model. Say "hi". Create a model called "Imagine" and
**Expected Behavior:**
I expect the custom model to obey the instruction placed on "System Prompt"
**Actual Behavior:**
Model provides response as if the custom "System Prompt" did not exist.
## Environment
Open WebUI Version: v0.3.1
Ollama Version: 0.1.42
- **Operating System: Ubuntu in WSL, on Windows 11
## Reproduction Details
**Confirmation:**
- [O] I have read and followed all the instructions provided in the README.md.
- [O] I am on the latest version of both Open WebUI and Ollama.
- [X] I have included the browser console logs.
- [O] I have included the Docker container logs.
## Logs and Screenshots
[docker.log](https://github.com/user-attachments/files/15776367/docker.log)
**Browser Console Logs:**
[Include relevant browser console logs, if applicable]
**Docker Container Logs:**
[Include relevant Docker container logs, if applicable]
**Screenshots (if applicable):**
[Attach any relevant screenshots to help illustrate the issue]
## Installation Method
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
<!-- gh-comment-id:2158963451 -->
@tjbck commented on GitHub (Jun 10, 2024):
Seems to be a model specific issue here.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @DraculaVladimir on GitHub (Jun 10, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/2987
Bug Report
Description
Custom Model not loading instructions when loading through "@"
Bug Summary:
Custom Model not loading instructions when loading through "@"
Steps to Reproduce:
Load any model. Say "hi". Create a model called "Imagine" and
Expected Behavior:
I expect the custom model to obey the instruction placed on "System Prompt"
Actual Behavior:
Model provides response as if the custom "System Prompt" did not exist.
Environment
Open WebUI Version: v0.3.1
Ollama Version: 0.1.42
Reproduction Details
Confirmation:
Logs and Screenshots
docker.log
Browser Console Logs:
[Include relevant browser console logs, if applicable]
Docker Container Logs:
[Include relevant Docker container logs, if applicable]
Screenshots (if applicable):
[Attach any relevant screenshots to help illustrate the issue]
Installation Method
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
@tjbck commented on GitHub (Jun 10, 2024):
Seems to be a model specific issue here.