FabianGroeger commited on
Commit
c224a44
1 Parent(s): 3a406bc

initial upload of HotelBERT

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
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
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.11.3",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 36000
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c567c51f2bbc8b9dfd793712c73fc1e4779aa74715066196f1cc7762a74b19
3
+ size 569670115
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d542d64a1fe63229bdc52445f112593cfcbf89ebf4be468c6c91aeaa0b29b0ab
3
+ size 284844082
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1ef2dba33c5a3c8f5af1f26fe9b64aa4faecdeae4816df81dd658048e19aa2
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb55d4719f0a2b2d412f7a3a8724654097fb2f4e923fd1d373d6d87c7f0d755a
3
+ size 623
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fd9050f2284d7625e46759eb7caa21d5ac3ff548c3608173333f3d647ed1a3
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff