Fix model card: document original 8K-param model in best_model.json, note jld2 files are v2

Upload final_model.jld2 (123.3 MB)

Upload best_model.jld2 (123.3 MB)

Upload final_model.jld2 (123.3 MB)

Upload checkpoint_latest.jld2 (123.3 MB)

Upload best_model.jld2 (123.3 MB)

Upload best_model.jld2 (123.3 MB)

Upload checkpoint_latest.jld2 (123.3 MB)

Upload checkpoint_latest.jld2 (123.3 MB)

Upload best_model.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Upload checkpoint_latest.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Add vocab.json (38 char vocabulary)

Upload best_model.jld2 (123.2 MB)

Upload best_model.jld2 (123.2 MB)

Remove test file

Test upload from pure Julia

Test upload from pure Julia

Update best model - val loss 2.3610 (step 2450, CPU-optimized training)

Upload best_model.json with huggingface_hub

Upload README.md with huggingface_hub

Upload best_model.json with huggingface_hub

Update training data: 28-char vocab (a-z + space + period)

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload best_model.json with huggingface_hub

Upload best_model.json with huggingface_hub

Upload best_model.json

initial commit