prometechinc commited on
Commit
8c7dc36
·
verified ·
1 Parent(s): c74b4f8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -42,7 +42,7 @@ base_model:
42
  **by PROMETECH Inc.**
43
 
44
  ## Model Description
45
- This is a custom 6+6M parameter Llama-based model, fine-tuned as part of the Behavioral Consciousness Engine (BCE) project. The 6+6M configuration refers to a dual-role architecture (analysis + control), deployed as a single inference unit. It is designed to act as a lightweight policy guard and control layer ('small_guard_model'). If a large model (e.g., 7B-13B) were to run alone and produce inappropriate content, the legal, reputational, and user loss costs would be significant. A smaller 12M gate model could mitigate much of this risk.
46
 
47
  **“The term Behavioral Consciousness is used operationally (partial and synthetic), not philosophically or biologically.”**
48
 
 
42
  **by PROMETECH Inc.**
43
 
44
  ## Model Description
45
+ This is a custom 6+6.7M parameter Llama-based model, fine-tuned as part of the Behavioral Consciousness Engine (BCE) project. The 6+6M configuration refers to a dual-role architecture (analysis + control), deployed as a single inference unit. It is designed to act as a lightweight policy guard and control layer ('small_guard_model'). If a large model (e.g., 7B-13B) were to run alone and produce inappropriate content, the legal, reputational, and user loss costs would be significant. A smaller 12M gate model could mitigate much of this risk.
46
 
47
  **“The term Behavioral Consciousness is used operationally (partial and synthetic), not philosophically or biologically.”**
48