Upload 2 files
Browse files- models/Dnikud_best_model.pth +3 -0
- models/config.yml +78 -0
models/Dnikud_best_model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3aa406f137cd12f036fad66053e62c9497aaa6e3ae451a0f00c3a7a129b281e
|
3 |
+
size 134
|
models/config.yml
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
_commit_hash: 41265b09a862144b2517afdfd46da4388f1380df
|
2 |
+
_name_or_path: tau/tavbert-he
|
3 |
+
add_cross_attention: false
|
4 |
+
architectures:
|
5 |
+
- RobertaForMaskedLM
|
6 |
+
attention_probs_dropout_prob: 0.1
|
7 |
+
bad_words_ids: null
|
8 |
+
begin_suppress_tokens: null
|
9 |
+
bos_token_id: 0
|
10 |
+
chunk_size_feed_forward: 0
|
11 |
+
classifier_dropout: null
|
12 |
+
cross_attention_hidden_size: null
|
13 |
+
decoder_start_token_id: null
|
14 |
+
diversity_penalty: 0.0
|
15 |
+
do_sample: false
|
16 |
+
early_stopping: false
|
17 |
+
encoder_no_repeat_ngram_size: 0
|
18 |
+
eos_token_id: 2
|
19 |
+
exponential_decay_length_penalty: null
|
20 |
+
finetuning_task: null
|
21 |
+
forced_bos_token_id: null
|
22 |
+
forced_eos_token_id: null
|
23 |
+
gradient_checkpointing: false
|
24 |
+
hidden_act: gelu
|
25 |
+
hidden_dropout_prob: 0.1
|
26 |
+
hidden_size: 768
|
27 |
+
id2label:
|
28 |
+
0: LABEL_0
|
29 |
+
1: LABEL_1
|
30 |
+
initializer_range: 0.02
|
31 |
+
intermediate_size: 3072
|
32 |
+
is_decoder: false
|
33 |
+
is_encoder_decoder: false
|
34 |
+
label2id:
|
35 |
+
LABEL_0: 0
|
36 |
+
LABEL_1: 1
|
37 |
+
layer_norm_eps: 1.0e-05
|
38 |
+
length_penalty: 1.0
|
39 |
+
max_length: 512
|
40 |
+
max_position_embeddings: 2050
|
41 |
+
min_length: 0
|
42 |
+
model_type: roberta
|
43 |
+
no_repeat_ngram_size: 0
|
44 |
+
num_attention_heads: 12
|
45 |
+
num_beam_groups: 1
|
46 |
+
num_beams: 1
|
47 |
+
num_hidden_layers: 12
|
48 |
+
num_return_sequences: 1
|
49 |
+
output_attentions: false
|
50 |
+
output_hidden_states: false
|
51 |
+
output_scores: false
|
52 |
+
pad_token_id: 1
|
53 |
+
position_embedding_type: absolute
|
54 |
+
prefix: null
|
55 |
+
problem_type: null
|
56 |
+
pruned_heads: {}
|
57 |
+
remove_invalid_values: false
|
58 |
+
repetition_penalty: 1.0
|
59 |
+
return_dict: true
|
60 |
+
return_dict_in_generate: false
|
61 |
+
sep_token_id: null
|
62 |
+
suppress_tokens: null
|
63 |
+
task_specific_params: null
|
64 |
+
temperature: 1.0
|
65 |
+
tf_legacy_loss: false
|
66 |
+
tie_encoder_decoder: false
|
67 |
+
tie_word_embeddings: true
|
68 |
+
tokenizer_class: null
|
69 |
+
top_k: 50
|
70 |
+
top_p: 1.0
|
71 |
+
torch_dtype: null
|
72 |
+
torchscript: false
|
73 |
+
transformers_version: 4.6.0.dev0
|
74 |
+
type_vocab_size: 2
|
75 |
+
typical_p: 1.0
|
76 |
+
use_bfloat16: false
|
77 |
+
use_cache: true
|
78 |
+
vocab_size: 345
|