mdraw commited on
Commit
bde5eb5
1 Parent(s): bef7f03

Add German sentiment BERT finetuned on news data

Browse files

Based on https://huggingface.co/oliverguhr/german-sentiment-bert, with
additional training on news data.

See https://github.com/text-analytics-20/news-sentiment-development for
more information.

README.md CHANGED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ # German sentiment BERT finetuned on news data
2
+
3
+ Based on https://huggingface.co/oliverguhr/german-sentiment-bert, with
4
+ additional training on news data.
5
+
6
+ See https://github.com/text-analytics-20/news-sentiment-development for
7
+ more information.
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "data/finetuned-sentibert-checkpoint-225",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "finetuning_task": "germansentiment",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "positive",
15
+ "1": "negative",
16
+ "2": "neutral"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "negative": 1,
22
+ "neutral": 2,
23
+ "positive": 0
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "transformers_version": "4.3.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30000
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dcb1355a32df4e946eccbc1f6912558207110f4e87da7fa608287aae62d32d9
3
+ size 436421129
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/home/m4/.cache/huggingface/transformers/0be9cd8f70c135cbe0f6bf35cd771a593a4d6d3ab7c5835f5bc887dc0d4e1a22.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "oliverguhr/german-sentiment-bert", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff