Upload README.md with huggingface_hub

README.md

@@ -21,6 +21,13 @@ architectural axis from a shared baseline, trained on 1B tokens of
 (`sample-10BT`, GPT-2 tokenizer). Full paper, figures, and code:
 https://github.com/<your-username>/<your-repo> (GitHub repo URL — fill in once pushed).
 
+![Training and validation loss curves for all 19 models](images/loss_curves_all.png)
+
+<table><tr>
+<td><img src="images/bench_vs_ppl.png" alt="Zero-shot capability vs. validation perplexity"></td>
+<td><img src="images/pareto.png" alt="Perplexity vs. KV-cached decode speed Pareto trade-off"></td>
+</tr></table>
+
 Every subfolder (`m01/` ... `m19/`) is one model: `model.safetensors` (weights,
 optimizer state stripped), `config.json` (architecture + training hyperparameters),
 `eval_results.json` (perplexity / FLOPs / throughput / VRAM), and