salohnana2018
commited on
Commit
•
a54265d
1
Parent(s):
892e330
Upload model
Browse files- config.json +136 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
|
3 |
+
"adapters": {
|
4 |
+
"adapters": {
|
5 |
+
"ABSA_Sentiment_classification_HARD50_pfeiffer_Stack": "9076f36a74755ac4",
|
6 |
+
"mlm": "9ed5b5a29de19b71"
|
7 |
+
},
|
8 |
+
"config_map": {
|
9 |
+
"9076f36a74755ac4": {
|
10 |
+
"adapter_residual_before_ln": false,
|
11 |
+
"cross_adapter": false,
|
12 |
+
"factorized_phm_W": true,
|
13 |
+
"factorized_phm_rule": false,
|
14 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
15 |
+
"init_weights": "bert",
|
16 |
+
"inv_adapter": null,
|
17 |
+
"inv_adapter_reduction_factor": null,
|
18 |
+
"is_parallel": false,
|
19 |
+
"learn_phm": true,
|
20 |
+
"leave_out": [],
|
21 |
+
"ln_after": false,
|
22 |
+
"ln_before": false,
|
23 |
+
"mh_adapter": false,
|
24 |
+
"non_linearity": "relu",
|
25 |
+
"original_ln_after": true,
|
26 |
+
"original_ln_before": true,
|
27 |
+
"output_adapter": true,
|
28 |
+
"phm_bias": true,
|
29 |
+
"phm_c_init": "normal",
|
30 |
+
"phm_dim": 4,
|
31 |
+
"phm_init_range": 0.0001,
|
32 |
+
"phm_layer": false,
|
33 |
+
"phm_rank": 1,
|
34 |
+
"reduction_factor": 16,
|
35 |
+
"residual_before_ln": true,
|
36 |
+
"scaling": 1.0,
|
37 |
+
"shared_W_phm": false,
|
38 |
+
"shared_phm_rule": true,
|
39 |
+
"use_gating": false
|
40 |
+
},
|
41 |
+
"9ed5b5a29de19b71": {
|
42 |
+
"adapter_residual_before_ln": false,
|
43 |
+
"cross_adapter": false,
|
44 |
+
"factorized_phm_W": true,
|
45 |
+
"factorized_phm_rule": false,
|
46 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
47 |
+
"init_weights": "bert",
|
48 |
+
"inv_adapter": "nice",
|
49 |
+
"inv_adapter_reduction_factor": 2,
|
50 |
+
"is_parallel": false,
|
51 |
+
"learn_phm": true,
|
52 |
+
"leave_out": [],
|
53 |
+
"ln_after": false,
|
54 |
+
"ln_before": false,
|
55 |
+
"mh_adapter": false,
|
56 |
+
"non_linearity": "relu",
|
57 |
+
"original_ln_after": true,
|
58 |
+
"original_ln_before": true,
|
59 |
+
"output_adapter": true,
|
60 |
+
"phm_bias": true,
|
61 |
+
"phm_c_init": "normal",
|
62 |
+
"phm_dim": 4,
|
63 |
+
"phm_init_range": 0.0001,
|
64 |
+
"phm_layer": false,
|
65 |
+
"phm_rank": 1,
|
66 |
+
"reduction_factor": 16,
|
67 |
+
"residual_before_ln": true,
|
68 |
+
"scaling": 1.0,
|
69 |
+
"shared_W_phm": false,
|
70 |
+
"shared_phm_rule": true,
|
71 |
+
"use_gating": false
|
72 |
+
}
|
73 |
+
},
|
74 |
+
"fusion_config_map": {},
|
75 |
+
"fusions": {}
|
76 |
+
},
|
77 |
+
"architectures": [
|
78 |
+
"BertModelWithHeads"
|
79 |
+
],
|
80 |
+
"attention_probs_dropout_prob": 0.1,
|
81 |
+
"classifier_dropout": null,
|
82 |
+
"gradient_checkpointing": false,
|
83 |
+
"hidden_act": "gelu",
|
84 |
+
"hidden_dropout_prob": 0.1,
|
85 |
+
"hidden_size": 768,
|
86 |
+
"id2label": {
|
87 |
+
"0": "negative",
|
88 |
+
"1": "positive",
|
89 |
+
"2": "neutral"
|
90 |
+
},
|
91 |
+
"initializer_range": 0.02,
|
92 |
+
"intermediate_size": 3072,
|
93 |
+
"label2id": {
|
94 |
+
"negative": 0,
|
95 |
+
"neutral": 2,
|
96 |
+
"positive": 1
|
97 |
+
},
|
98 |
+
"layer_norm_eps": 1e-12,
|
99 |
+
"max_position_embeddings": 512,
|
100 |
+
"model_type": "bert",
|
101 |
+
"num_attention_heads": 12,
|
102 |
+
"num_hidden_layers": 12,
|
103 |
+
"pad_token_id": 0,
|
104 |
+
"position_embedding_type": "absolute",
|
105 |
+
"prediction_heads": {
|
106 |
+
"ABSA_Sentiment_classification_HARD50_pfeiffer_Stack": {
|
107 |
+
"activation_function": "tanh",
|
108 |
+
"bias": true,
|
109 |
+
"head_type": "classification",
|
110 |
+
"label2id": {
|
111 |
+
"negative": 0,
|
112 |
+
"neutral": 2,
|
113 |
+
"positive": 1
|
114 |
+
},
|
115 |
+
"layers": 2,
|
116 |
+
"num_labels": 3,
|
117 |
+
"use_pooler": false
|
118 |
+
},
|
119 |
+
"mlm": {
|
120 |
+
"activation_function": "gelu",
|
121 |
+
"bias": true,
|
122 |
+
"embedding_size": 768,
|
123 |
+
"head_type": "masked_lm",
|
124 |
+
"label2id": null,
|
125 |
+
"layer_norm": true,
|
126 |
+
"layers": 2,
|
127 |
+
"shift_labels": false,
|
128 |
+
"vocab_size": 30000
|
129 |
+
}
|
130 |
+
},
|
131 |
+
"torch_dtype": "float32",
|
132 |
+
"transformers_version": "4.26.1",
|
133 |
+
"type_vocab_size": 2,
|
134 |
+
"use_cache": true,
|
135 |
+
"vocab_size": 30000
|
136 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.26.1"
|
5 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bd590fe17e5d33379a9f685ab13affbb08fbec4b01ab34fc54caa0d689ba25
|
3 |
+
size 449640305
|