Add Usage section (merge best-of-both cards)

README.md

@@ -51,6 +51,25 @@ Note: a generic `lm-eval-harness` run scores BLiMP/ARC ~2-3pp higher than the Gl
 FineWeb-Edu, DCLM, StackExchange, open-web-math, FineMath, scientific papers, books/Gutenberg, code, CC-News.
 A decontaminated expansion to ~8.3B tokens (added FineWeb-Edu + OpenStax science) is used for later runs.
 
+## Usage
+
+These are raw nanoGPT-lineage checkpoints (plain `torch` state dicts), **not** `transformers`
+`AutoModel` weights. Architecture is inferable from tensor shapes (embedding `[vocab, d_model]`,
+layer count from keys) and the table above; the tokenizer is `tokenizers`-format.
+
+```python
+import torch
+from tokenizers import Tokenizer
+tok  = Tokenizer.from_file("tokenizer.json")           # BPE-12k, vocab 12288
+ckpt = torch.load("bpe16m_10B/ckpt.pt", map_location="cpu")
+state = ckpt.get("model", ckpt)                         # nanoGPT-style GPT
+# Rebuild a GPT with the shape from the table (e.g. L6 d408 h6, block 1024),
+# load_state_dict(state), then run token ids [B, T] through the forward.
+```
+
+For the exact board-scoring forward (Glint protocol: 256-token clip, raw log-prob), see
+`glint_parity_eval.py` in the project staging.
+
 ## Positioning (honest)
 
 Leaderboard positions are **reconstruction estimates**: we reverse-engineered and validated the board scoring