OpenWebUI/docs
1
0
Fork 0
mirror of https://github.com/open-webui/docs synced 2025-05-22 04:06:11 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update deepseekr1-dynamic.md

Browse Source
This commit is contained in:
Timothy Jaeryang Baek 2025-01-31 01:50:18 -08:00
parent 1461c0990a
commit 5829859e1e
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/tutorials/integrations/deepseekr1-dynamic.md
View File

@ -100,7 +100,7 @@ Here’s the command to start the server:
- **`--n-gpu-layers`:** Set the number of layers you want to offload to your GPU for faster inference. The exact number depends on your GPU’s memory capacity — reference Unsloth’s table for specific recommendations. - **`--n-gpu-layers`:** Set the number of layers you want to offload to your GPU for faster inference. The exact number depends on your GPU’s memory capacity — reference Unsloth’s table for specific recommendations.
::: :::
For example, if your model was downloaded to `/Users/tim/Documents/workspace` and you have an RTX 4090 GPU with 24GB VRAM, your command would look like this: For example, if your model was downloaded to `/Users/tim/Documents/workspace`, your command would look like this:
```bash ```bash
./llama-server \ ./llama-server \
--model /Users/tim/Documents/workspace/DeepSeek-R1-GGUF/DeepSeek-R1-UD-IQ1_S/DeepSeek-R1-UD-IQ1_S-00001-of-00003.gguf \ --model /Users/tim/Documents/workspace/DeepSeek-R1-GGUF/DeepSeek-R1-UD-IQ1_S/DeepSeek-R1-UD-IQ1_S-00001-of-00003.gguf \