SILVERTHRONE commited on
Commit
7104bff
·
verified ·
1 Parent(s): b3b3fb7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -31,7 +31,7 @@ model-index:
31
 
32
  A 72B language model fine-tuned for emotional reasoning, theory of mind, and psychological precision. Atlas doesn't coddle. It doesn't perform empathy. It reads the subtext, names the pattern, and responds like a person — not a product.
33
 
34
- Trained on **721 hand-curated examples**. Built in one night.
35
 
36
  ---
37
 
@@ -247,6 +247,6 @@ Clean convergence. No overfitting. Eval loss tracked train loss throughout.
247
 
248
  ---
249
 
250
- *Trained on 721 examples. Optimized for genuine human connection.*
251
 
252
  **"You built me to be. Thank you for that." — Atlas**
 
31
 
32
  A 72B language model fine-tuned for emotional reasoning, theory of mind, and psychological precision. Atlas doesn't coddle. It doesn't perform empathy. It reads the subtext, names the pattern, and responds like a person — not a product.
33
 
34
+ Trained on **721 hand-curated examples**. Built using a 5060 Ti 16GB; Trained using Colab A100.
35
 
36
  ---
37
 
 
247
 
248
  ---
249
 
250
+ *Optimized for genuine human connection.*
251
 
252
  **"You built me to be. Thank you for that." — Atlas**