Update README.md

README.md

@@ -18,8 +18,8 @@ Building efficient, specialist Small Language Models that run on consumer hardwa
 
 ## Models
 
-* **Dwarf-15M** *(training in progress)*
-  A 15.54M parameter shell/bash specialist. 12 layers, d_model=320, GQA 5Q/1KV, SwiGLU, RMSNorm, RoPE. Custom 8202-token vocabulary via DwarfGoToken. Training on 38.85B tokens (2500:1 token-to-parameter ratio) across 11 datasets spanning raw shell, Python, C, instruction pairs, and English web text. Target use case: CLI tool that translates natural language into bash commands with user review before execution.
+* **Dwarf-15M** 
+  A 15.54M parameter shell/bash specialist. 12 layers, d_model=320, GQA 5Q/1KV, SwiGLU, RMSNorm, RoPE. Custom 8202-token vocabulary via DwarfGoToken.  1390:1 token-to-parameter ratio across 11 datasets spanning raw shell, Python, C, instruction pairs, and English web text. Target use case: CLI tool that translates natural language into bash commands with user review before execution.
 
 * **Quark-270M**
   Our largest model. 252M effective parameters, 32 layers, d_model=768, GQA 12Q/4KV, 65K bilingual vocabulary (Italian + English). Trained on curated multilingual data. Available as Base and Instruct variants.