Moreno La Quatra
training config v1 model
9afde18
-
1.38 kB
Upload it-en.tsv
-
7.96 kB
Upload MLM.png
-
25 Bytes
initial commit
best_mt_train_state_468500.pkl
Detected Pickle imports (8)
- "optax._src.transform.ScaleByScheduleState",
- "optax._src.transform.ScaleByAdamState",
- "numpy.dtype",
- "numpy.ndarray",
- "jax._src.device_array.reconstruct_device_array",
- "numpy.core.multiarray._reconstruct",
- "optax._src.base.EmptyState",
- "__main__.TrainingState"
How to fix it?
218 MB
Upload MT ckp
-
886 kB
Upload en_tokenizer_1M.json
-
43.5 MB
Upload it-en.tsv
-
844 kB
Upload tokenizer for MT
-
69.5 kB
Upload tatoeba_example.png
-
235 Bytes
training config v1 model
v1_mlm_train_state_362000.pkl
Detected Pickle imports (8)
- "__main__.TrainingState",
- "optax._src.transform.ScaleByAdamState",
- "numpy.ndarray",
- "optax._src.base.EmptyState",
- "numpy.dtype",
- "numpy.core.multiarray._reconstruct",
- "optax._src.transform.ScaleByScheduleState",
- "jax._src.device_array.reconstruct_device_array"
How to fix it?
86.9 MB
Upload v1_mlm_train_state_362000.pkl
