Correct parameter count to 2.82B (value embeddings were uncounted)

README.md

@@ -70,7 +70,7 @@ Its `sft/` directory holds six fine-tuning variants. The one shipped as
 `pre1930-curriculum-c3-robust-v2`; the others — `karpathy-modern-sft-v1`,
 `nanochat-default-datamatch-v1`, `c3-robust`, and two `c3-robust-v3` configs — are kept here.
 
-`clean1930s-d24-r12-ctx4096-sssl-fulltok-v1` is the d24 / 730M run; its tokenizer is the one every
+`clean1930s-d24-r12-ctx4096-sssl-fulltok-v1` is the d24 / 1.38B run; its tokenizer is the one every
 midtrain mixture was built against.
 
 > **Note.** Each `config.json` records repo and dataset names as they were at training time