Commit History
-
Explicitly set model_max_length in the tokenizer config.
Milan Straka98c2170
-
Add scripts used to generate v1.1.
Milan Strakaa75ff23 -
Describe that we dropped the pooler in v1.1.
Milan Straka20ab64f -
Better formulation.
Milan Straka41cfe08 -
Release version 1.1 of RobeCzech.
Milan StrakaIn version 1.1, the tokenizer was modified by (a) removing the hole, (b) mapping all tokens to a unique ID. That also required increasing the vocabulary sizes and embeddings weights (by replicating the embedding of the `[UNK]` token). Without finetuning, version 1.1 and version 1.0 gives exactly the same results on any input, and the tokens in version 1.0 that mapped to a different ID than the `[UNK]` token map to the same ID in version 1.1. However, the sizes of the embeddings (and LM head weights and biases) are different, so the weights of the version 1.1 are not compatible with the configuration of version 1.0 and vice versa.354716a
-
Add a link to a post describing the non-standard RobeCzech tokenizer.
8a75d1f
-
Adding `safetensors` variant of this model (#3)
- Adding `safetensors` variant of this model (06c409bb7898757f2730437fb50ba82648e8f254) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>7895163
-
Add serialized fast tokenizer.
6db0a84
-
Update the model card.
Milan Straka935d8d1 -
model documentation (#2)
- model documentation (923864124976874b83d79503644d11e863b2f2c5) Co-authored-by: Nazneen Rajani <nazneen@users.noreply.huggingface.co>e1eaff9
-
Add the missing -sa in the license.
b154a97
-
Add link to arXiv.
ed5ecf3
-
More information to the README.
Milan Strakac18d4a5 -
Add explicit LICENSE.
Milan Straka244c984 -
Add RobeCzech checkpoint.
Milan Strakab4fda3e
-
Update README.md
e75fab4 -
Update README.md
0a90c02 -
Initial upload.
8e5fa30 -
initial commit
b2cba52
