Hugging Face's logo

joelniklaus
/
legal-german-roberta-base

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
1
joelniklaus commited on
Commit
316bec5
•
1 Parent(s): 1f6148a

Model save

Browse files
Files changed (11) hide show
  1. last-checkpoint/config.json +0 -27
  2. last-checkpoint/optimizer.pt +0 -3
  3. last-checkpoint/pytorch_model.bin +0 -3
  4. last-checkpoint/rng_state.pth +0 -3
  5. last-checkpoint/scaler.pt +0 -3
  6. last-checkpoint/scheduler.pt +0 -3
  7. last-checkpoint/special_tokens_map.json +0 -9
  8. last-checkpoint/tokenizer.json +0 -0
  9. last-checkpoint/tokenizer_config.json +0 -13
  10. last-checkpoint/trainer_state.json +0 -0
  11. last-checkpoint/training_args.bin +0 -3
last-checkpoint/config.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "_name_or_path": "/scratch/users/jniklaus/MultilingualLMPretraining/data/plms/legal-german-roberta-base",
3
- "architectures": [
4
- "RobertaForMaskedLM"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 1,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
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": 0,
21
- "position_embedding_type": "absolute",
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.20.1",
24
- "type_vocab_size": 1,
25
- "use_cache": true,
26
- "vocab_size": 32000
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e5a92f11128c60bae53e142b40413437208f5b8c48d647384f7155fa97b3238
3
- size 885330713
 
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b4259dfdc9d95d40bfcdd98b7cbe401b1f4e0ac89f3aee63b1c92426a50e86b
3
- size 442678571
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a8c5011437bb6a4b42e3427dd3a9a6650136424f9f2781ff1ae4fc747298ec
3
- size 17563
 
 
 
 
last-checkpoint/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1972554f4c7d872911a1ab4e0fd839fb51f0fb3051ee3a13ef5ecb7c7c14439
3
- size 559
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c62aba35c522b0e30aa960a3ecaac259d22e10553ef1443be4a8e96f7c73f8aa
3
- size 623
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": "<mask>",
6
- "pad_token": "<pad>",
7
- "sep_token": "</s>",
8
- "unk_token": "<unk>"
9
- }
 
 
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": "<mask>",
6
- "model_max_length": 512,
7
- "name_or_path": "/scratch/users/jniklaus/MultilingualLMPretraining/data/plms/legal-german-roberta-base",
8
- "pad_token": "<pad>",
9
- "sep_token": "</s>",
10
- "special_tokens_map_file": "data/plms/legal-german-roberta-base_32k/special_tokens_map.json",
11
- "tokenizer_class": "PreTrainedTokenizerFast",
12
- "unk_token": "<unk>"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e25faf06c9975aea2aa997e353bc16bb59f3eabd76c81f0c49c46d732c973aeb
3
- size 3503