Upload README.md with huggingface_hub

Update eval_results.json: probes + diagnostics from run_evals_backbone.py

Upload README.md with huggingface_hub

v1.0.0: searchless_chess vocab, 512 context, 200K steps

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Restore complete metrics (10201 records, 200 val, 20 with extended fields)

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Restore complete metrics (10201 records, 200 val, 20 with extended fields)

Upload metrics.jsonl with huggingface_hub

Fix citation.

Add base_model links and citation to frontmatter

Add citation to YAML frontmatter

Model card: unconditioned ceiling, games seen, architecture in frontmatter

Model card: add architecture to frontmatter, legal rate first, full metrics

Fix model card: table rendering, remove empty columns

Fix model-index: add required dataset field

Fix frontmatter: numeric metrics, remove invalid dataset ref

Add eval results (probes + diagnostics)

Add model card with eval results and citation

Training run: 100K steps (squash-merge from run/run_20260325_002657_small_zesty-osprey)

Link to HuggingFace repo mirror

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit