Gen-HVAC commited on
Commit
d719cc9
·
verified ·
1 Parent(s): 50abebb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -141,10 +141,8 @@ We condition on different RTG for comfort and energy savings. Anykind of data wi
141
  actions lead to what kind of consequenses.
142
 
143
  5) LLM deployment phase
144
-
145
- After this you have to move on to the inference Server side to tie up all these together
146
  Gen-HVAC supports an optional LLM + Digital Human-in-the-Loop (DHIL) layer that modulates preference/RTG targets and high-level
147
- constraints while the controller produces smooth setpoint sequences. For local LLM hosting, install Ollama, pull a quantized model
148
  , and launch the service.
149
 
150
  On Linux/macOS you can install Ollama via curl -fsSL https://ollama.com/install.sh | sh, start the daemon with ollama serve (leave it running), and pull recommended models using ollama pull deepseek-r1:7b (lightweight reasoning), ollama pull llama3.1:8b (strong general instruction-following), ollama pull qwen2.5:7b (efficient general model), or ollama pull mistral:instruct (fast instruct model). If you want a slightly heavier but still practical model, ollama pull deepseek-r1:14b or ollama pull qwen2.5:14b.
 
141
  actions lead to what kind of consequenses.
142
 
143
  5) LLM deployment phase
 
 
144
  Gen-HVAC supports an optional LLM + Digital Human-in-the-Loop (DHIL) layer that modulates preference/RTG targets and high-level
145
+ constraints. For local LLM hosting, install Ollama, pull a quantized model
146
  , and launch the service.
147
 
148
  On Linux/macOS you can install Ollama via curl -fsSL https://ollama.com/install.sh | sh, start the daemon with ollama serve (leave it running), and pull recommended models using ollama pull deepseek-r1:7b (lightweight reasoning), ollama pull llama3.1:8b (strong general instruction-following), ollama pull qwen2.5:7b (efficient general model), or ollama pull mistral:instruct (fast instruct model). If you want a slightly heavier but still practical model, ollama pull deepseek-r1:14b or ollama pull qwen2.5:14b.