Llama-cpp: Difference between revisions

Woile (talk | contribs)
m remove comments to avoid distraction
Woile (talk | contribs)
m use unsloth instead of bartowski models
Line 147: Line 147:


In your shell:<syntaxhighlight lang="bash">llama-cli \  
In your shell:<syntaxhighlight lang="bash">llama-cli \  
   -hf bartowski/Qwen_Qwen3-Coder-Next-GGUF:Q4_K_M \  
   -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M \  
   --temp 1.0 --top-p 0.95 --top-k 40 \  
   --temp 1.0 --top-p 0.95 --top-k 40 \  
   -p "briefly explain journalctl in one paragraph"</syntaxhighlight>
   -p "briefly explain journalctl in one paragraph"</syntaxhighlight>
Line 157: Line 157:
You can manually start the server from your terminal, it's usage, is not that different from <code>llama-cli</code>, <syntaxhighlight lang="bash">
You can manually start the server from your terminal, it's usage, is not that different from <code>llama-cli</code>, <syntaxhighlight lang="bash">
llama-server \
llama-server \
     -hf bartowski/Qwen_Qwen3-Coder-Next-GGUF:Q4_K_M \  
     -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_M \  
     --temp 1.0 --top-p 0.95 --top-k 40  
     --temp 1.0 --top-p 0.95 --top-k 40  
</syntaxhighlight>
</syntaxhighlight>