Skip to content

Replace HTML entities with actual characters so they render correctly in the docs #497

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
privatejava wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Replace HTML entities with actual characters so they render correctly in the docs #497

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/features/shell-integration.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -426,7 +426,7 @@ This setup works reliably on Windows systems using Cygwin, Fish, and the Starshi

**Issue**: Commands that span multiple lines can confuse Roo and may show output from previous commands mixed in with current output.

**Workaround**: Instead of multi-line commands, use command chaining with `&&` to keep everything on one line (e.g., `echo a && echo b` instead of typing each command on a separate line).
**Workaround**: Instead of multi-line commands, use command chaining with `&&` to keep everything on one line (e.g., `echo a && echo b` instead of typing each command on a separate line).

#### PowerShell-Specific Issues

Expand Down
12 changes: 6 additions & 6 deletions docs/providers/ollama.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,20 +135,20 @@ If no model instance is running, Ollama spins one up on demand. During that cold
**Fixes**
1. **Preload the model**
```bash
ollama run <model-name>
ollama run <model-name>
```
Keep it running, then issue the request from Roo.

2. **Pin the context window (`num_ctx`)**
- Option A — interactive session, then save:
```bash
# inside `ollama run &lt;base-model&gt;`
# inside `ollama run <base-model>`
/set parameter num_ctx 32768
/save &lt;your_model_name&gt;
/save <your_model_name>
```
- Option B — Modelfile (recommended for reproducibility):
```dockerfile
FROM &lt;base-model&gt;
FROM <base-model>
PARAMETER num_ctx 32768
# Adjust based on your available memory:
# 16384 for ~8GB VRAM
Expand All @@ -157,7 +157,7 @@ If no model instance is running, Ollama spins one up on demand. During that cold
```
Then create the model:
```bash
ollama create &lt;your_model_name&gt; -f Modelfile
ollama create <your_model_name> -f Modelfile
```

3. **Ensure the model's context window is pinned**
Expand All @@ -169,7 +169,7 @@ If no model instance is running, Ollama spins one up on demand. During that cold
5. **Restart after an OOM**
```bash
ollama ps
ollama stop &lt;model-name&gt;
ollama stop <model-name>
```

**Quick checklist**
Expand Down