thomas-schweich
/

pawn-small

next-token-prediction

representation-learning

Eval Results (legacy)

Model card Files Files and versions

4.52 GB

Ctrl+K

Ctrl+K

1 contributor

History: 27 commits

thomas-schweich's picture

thomas-schweich

Upload README.md with huggingface_hub

1daec5b verified about 21 hours ago

checkpoints
v1.0.0: searchless_chess vocab, 512 context, 200K steps 1 day ago
.gitattributes

1.52 kB
initial commit 26 days ago
README.md

11.5 kB
Upload README.md with huggingface_hub about 21 hours ago
config.json

997 Bytes
v1.0.0: searchless_chess vocab, 512 context, 200K steps 1 day ago
eval_results.json

20.2 kB
Update eval_results.json: probes + diagnostics from run_evals_backbone.py about 21 hours ago
metrics.jsonl

2.2 MB
v1.0.0: searchless_chess vocab, 512 context, 200K steps 1 day ago
model.pt
Detected Pickle imports (4)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage",
- "torch.ByteStorage"
What is a pickle import?
114 MB
xet

Upload folder using huggingface_hub 26 days ago
model.safetensors

35.8 MB
xet

v1.0.0: searchless_chess vocab, 512 context, 200K steps 1 day ago
optimizer.safetensors

71.5 MB
xet

v1.0.0: searchless_chess vocab, 512 context, 200K steps 1 day ago
training_state.json

8.65 kB
v1.0.0: searchless_chess vocab, 512 context, 200K steps 1 day ago