Hugging Face's logo

macedonizer
/
mk-roberta-base

Fill-Mask
Transformers
PyTorch
JAX
Macedonian
roberta
masked-lm
Inference Endpoints
Model card Files Community
Stojanco Tudzarski commited on
Commit
f8f498b
•
1 Parent(s): 4844607

back to original push

Browse files
Files changed (6) hide show
  1. config.json +3 -4
  2. optimizer.pt +0 -3
  3. pytorch_model.bin +2 -2
  4. scheduler.pt +1 -1
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "./mk-roberta-base/checkpoint-320000",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
@@ -12,15 +11,15 @@
12
  "hidden_size": 768,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 514,
17
  "model_type": "roberta",
18
  "num_attention_heads": 12,
19
- "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "transformers_version": "4.4.2",
23
  "type_vocab_size": 1,
24
  "use_cache": true,
25
- "vocab_size": 50265
26
  }
 
1
  {
 
2
  "architectures": [
3
  "RobertaForMaskedLM"
4
  ],
 
11
  "hidden_size": 768,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 514,
16
  "model_type": "roberta",
17
  "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
  "pad_token_id": 1,
20
  "position_embedding_type": "absolute",
21
  "transformers_version": "4.4.2",
22
  "type_vocab_size": 1,
23
  "use_cache": true,
24
+ "vocab_size": 52000
25
  }
optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:683dd3f09ce256e677eb4b6e62fa15fd28109d473d22f889a6c3b8ae7725f436
3
- size 997706595
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:421a0d8a203794691ce37f523ba0a77b2f3325e8c38607b3e7fc2266c318215d
3
- size 498880850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de14c83d1079fa3df3415d4a6f3e0032b5961d15576af2ca7c7364111c32abf6
3
+ size 334067506
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2af33f18d2df7888c417ee6da920215723758d0d4ee8275a0d8e815173cbd3a
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30834c9eacd278233301e5743cc24659976bc3e5f25f5b70bde06c4f27d0334
3
  size 623
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b449e56852c450c1d4c9cac4f150b52769d097166ddeb18ec34f82ba7eef4c2
3
  size 2287
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef99a94cdac6dbe7a598d14bbe06802a17e3accbb209ee42d18bc203ee14ed55
3
  size 2287