Commit
•
0cabc94
1
Parent(s):
9386147
Upload MultiHead_MultiLabel_XL
Browse files- config.json +109 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +770 -0
config.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/vasters/touche24/touche-Sotiris/xlm-roberta-xl-38-layers-5e-6-all-dir/checkpoint-74580",
|
3 |
+
"architectures": [
|
4 |
+
"MultiHead_MultiLabel_XL"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 2560,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Self-direction: thought attained",
|
15 |
+
"1": "Self-direction: thought constrained",
|
16 |
+
"2": "Self-direction: action attained",
|
17 |
+
"3": "Self-direction: action constrained",
|
18 |
+
"4": "Stimulation attained",
|
19 |
+
"5": "Stimulation constrained",
|
20 |
+
"6": "Hedonism attained",
|
21 |
+
"7": "Hedonism constrained",
|
22 |
+
"8": "Achievement attained",
|
23 |
+
"9": "Achievement constrained",
|
24 |
+
"10": "Power: dominance attained",
|
25 |
+
"11": "Power: dominance constrained",
|
26 |
+
"12": "Power: resources attained",
|
27 |
+
"13": "Power: resources constrained",
|
28 |
+
"14": "Face attained",
|
29 |
+
"15": "Face constrained",
|
30 |
+
"16": "Security: personal attained",
|
31 |
+
"17": "Security: personal constrained",
|
32 |
+
"18": "Security: societal attained",
|
33 |
+
"19": "Security: societal constrained",
|
34 |
+
"20": "Tradition attained",
|
35 |
+
"21": "Tradition constrained",
|
36 |
+
"22": "Conformity: rules attained",
|
37 |
+
"23": "Conformity: rules constrained",
|
38 |
+
"24": "Conformity: interpersonal attained",
|
39 |
+
"25": "Conformity: interpersonal constrained",
|
40 |
+
"26": "Humility attained",
|
41 |
+
"27": "Humility constrained",
|
42 |
+
"28": "Benevolence: caring attained",
|
43 |
+
"29": "Benevolence: caring constrained",
|
44 |
+
"30": "Benevolence: dependability attained",
|
45 |
+
"31": "Benevolence: dependability constrained",
|
46 |
+
"32": "Universalism: concern attained",
|
47 |
+
"33": "Universalism: concern constrained",
|
48 |
+
"34": "Universalism: nature attained",
|
49 |
+
"35": "Universalism: nature constrained",
|
50 |
+
"36": "Universalism: tolerance attained",
|
51 |
+
"37": "Universalism: tolerance constrained"
|
52 |
+
},
|
53 |
+
"initializer_range": 0.02,
|
54 |
+
"intermediate_size": 10240,
|
55 |
+
"label2id": {
|
56 |
+
"Achievement attained": 8,
|
57 |
+
"Achievement constrained": 9,
|
58 |
+
"Benevolence: caring attained": 28,
|
59 |
+
"Benevolence: caring constrained": 29,
|
60 |
+
"Benevolence: dependability attained": 30,
|
61 |
+
"Benevolence: dependability constrained": 31,
|
62 |
+
"Conformity: interpersonal attained": 24,
|
63 |
+
"Conformity: interpersonal constrained": 25,
|
64 |
+
"Conformity: rules attained": 22,
|
65 |
+
"Conformity: rules constrained": 23,
|
66 |
+
"Face attained": 14,
|
67 |
+
"Face constrained": 15,
|
68 |
+
"Hedonism attained": 6,
|
69 |
+
"Hedonism constrained": 7,
|
70 |
+
"Humility attained": 26,
|
71 |
+
"Humility constrained": 27,
|
72 |
+
"Power: dominance attained": 10,
|
73 |
+
"Power: dominance constrained": 11,
|
74 |
+
"Power: resources attained": 12,
|
75 |
+
"Power: resources constrained": 13,
|
76 |
+
"Security: personal attained": 16,
|
77 |
+
"Security: personal constrained": 17,
|
78 |
+
"Security: societal attained": 18,
|
79 |
+
"Security: societal constrained": 19,
|
80 |
+
"Self-direction: action attained": 2,
|
81 |
+
"Self-direction: action constrained": 3,
|
82 |
+
"Self-direction: thought attained": 0,
|
83 |
+
"Self-direction: thought constrained": 1,
|
84 |
+
"Stimulation attained": 4,
|
85 |
+
"Stimulation constrained": 5,
|
86 |
+
"Tradition attained": 20,
|
87 |
+
"Tradition constrained": 21,
|
88 |
+
"Universalism: concern attained": 32,
|
89 |
+
"Universalism: concern constrained": 33,
|
90 |
+
"Universalism: nature attained": 34,
|
91 |
+
"Universalism: nature constrained": 35,
|
92 |
+
"Universalism: tolerance attained": 36,
|
93 |
+
"Universalism: tolerance constrained": 37
|
94 |
+
},
|
95 |
+
"layer_norm_eps": 1e-05,
|
96 |
+
"max_position_embeddings": 514,
|
97 |
+
"model_type": "xlm-roberta-xl",
|
98 |
+
"num_attention_heads": 32,
|
99 |
+
"num_hidden_layers": 36,
|
100 |
+
"pad_token_id": 1,
|
101 |
+
"position_embedding_type": "absolute",
|
102 |
+
"problem_type": "multi_label_classification",
|
103 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
104 |
+
"torch_dtype": "float32",
|
105 |
+
"transformers_version": "4.40.2",
|
106 |
+
"type_vocab_size": 1,
|
107 |
+
"use_cache": true,
|
108 |
+
"vocab_size": 250041
|
109 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19e3393812f6797ad93f6d08af2a48b2c7504de103e8ab0d16a1f9f0c5e007b1
|
3 |
+
size 4978468240
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb2975b866c4b6ecb736b8c58be1d79ac398e2cb4a207fd8c46558a271131a8d
|
3 |
+
size 4930427680
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64bfd5595c5155cac062ece12c2b2dad41a5f302409e9a5df5b31703656f273b
|
3 |
+
size 4904992464
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bba545d2f5b04307e08bbca856e80ccbc6b75da2e1812cc068d134de91f76c9
|
3 |
+
size 2179438384
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,770 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 16993230168
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"language_heads.BG.dense.bias": "model-00004-of-00004.safetensors",
|
7 |
+
"language_heads.BG.dense.weight": "model-00004-of-00004.safetensors",
|
8 |
+
"language_heads.BG.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
9 |
+
"language_heads.BG.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
10 |
+
"language_heads.BG.extra_transformer_layer_1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
|
11 |
+
"language_heads.BG.extra_transformer_layer_1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
|
12 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self.key.bias": "model-00004-of-00004.safetensors",
|
13 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self.key.weight": "model-00004-of-00004.safetensors",
|
14 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self.query.bias": "model-00004-of-00004.safetensors",
|
15 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self.query.weight": "model-00004-of-00004.safetensors",
|
16 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self.value.bias": "model-00004-of-00004.safetensors",
|
17 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self.value.weight": "model-00004-of-00004.safetensors",
|
18 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
|
19 |
+
"language_heads.BG.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
|
20 |
+
"language_heads.BG.extra_transformer_layer_1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
|
21 |
+
"language_heads.BG.extra_transformer_layer_1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
|
22 |
+
"language_heads.BG.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
23 |
+
"language_heads.BG.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
24 |
+
"language_heads.BG.out_proj.bias": "model-00004-of-00004.safetensors",
|
25 |
+
"language_heads.BG.out_proj.weight": "model-00004-of-00004.safetensors",
|
26 |
+
"language_heads.DE.dense.bias": "model-00004-of-00004.safetensors",
|
27 |
+
"language_heads.DE.dense.weight": "model-00004-of-00004.safetensors",
|
28 |
+
"language_heads.DE.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
29 |
+
"language_heads.DE.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
30 |
+
"language_heads.DE.extra_transformer_layer_1.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
31 |
+
"language_heads.DE.extra_transformer_layer_1.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
32 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
33 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
34 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
35 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
36 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
37 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
38 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
39 |
+
"language_heads.DE.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
40 |
+
"language_heads.DE.extra_transformer_layer_1.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
41 |
+
"language_heads.DE.extra_transformer_layer_1.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
42 |
+
"language_heads.DE.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
43 |
+
"language_heads.DE.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
44 |
+
"language_heads.DE.out_proj.bias": "model-00004-of-00004.safetensors",
|
45 |
+
"language_heads.DE.out_proj.weight": "model-00004-of-00004.safetensors",
|
46 |
+
"language_heads.EL.dense.bias": "model-00003-of-00004.safetensors",
|
47 |
+
"language_heads.EL.dense.weight": "model-00003-of-00004.safetensors",
|
48 |
+
"language_heads.EL.extra_transformer_layer_1.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
49 |
+
"language_heads.EL.extra_transformer_layer_1.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
50 |
+
"language_heads.EL.extra_transformer_layer_1.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
51 |
+
"language_heads.EL.extra_transformer_layer_1.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
52 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
53 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
54 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
55 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
56 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
57 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
58 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
59 |
+
"language_heads.EL.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
60 |
+
"language_heads.EL.extra_transformer_layer_1.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
61 |
+
"language_heads.EL.extra_transformer_layer_1.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
62 |
+
"language_heads.EL.extra_transformer_layer_1.output.dense.bias": "model-00003-of-00004.safetensors",
|
63 |
+
"language_heads.EL.extra_transformer_layer_1.output.dense.weight": "model-00003-of-00004.safetensors",
|
64 |
+
"language_heads.EL.out_proj.bias": "model-00003-of-00004.safetensors",
|
65 |
+
"language_heads.EL.out_proj.weight": "model-00003-of-00004.safetensors",
|
66 |
+
"language_heads.EN.dense.bias": "model-00003-of-00004.safetensors",
|
67 |
+
"language_heads.EN.dense.weight": "model-00003-of-00004.safetensors",
|
68 |
+
"language_heads.EN.extra_transformer_layer_1.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
69 |
+
"language_heads.EN.extra_transformer_layer_1.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
70 |
+
"language_heads.EN.extra_transformer_layer_1.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
71 |
+
"language_heads.EN.extra_transformer_layer_1.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
72 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
73 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
74 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
75 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
76 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
77 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
78 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
79 |
+
"language_heads.EN.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
80 |
+
"language_heads.EN.extra_transformer_layer_1.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
81 |
+
"language_heads.EN.extra_transformer_layer_1.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
82 |
+
"language_heads.EN.extra_transformer_layer_1.output.dense.bias": "model-00003-of-00004.safetensors",
|
83 |
+
"language_heads.EN.extra_transformer_layer_1.output.dense.weight": "model-00003-of-00004.safetensors",
|
84 |
+
"language_heads.EN.out_proj.bias": "model-00003-of-00004.safetensors",
|
85 |
+
"language_heads.EN.out_proj.weight": "model-00003-of-00004.safetensors",
|
86 |
+
"language_heads.FR.dense.bias": "model-00004-of-00004.safetensors",
|
87 |
+
"language_heads.FR.dense.weight": "model-00004-of-00004.safetensors",
|
88 |
+
"language_heads.FR.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
89 |
+
"language_heads.FR.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
90 |
+
"language_heads.FR.extra_transformer_layer_1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
|
91 |
+
"language_heads.FR.extra_transformer_layer_1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
|
92 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self.key.bias": "model-00004-of-00004.safetensors",
|
93 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self.key.weight": "model-00004-of-00004.safetensors",
|
94 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self.query.bias": "model-00004-of-00004.safetensors",
|
95 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self.query.weight": "model-00004-of-00004.safetensors",
|
96 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self.value.bias": "model-00004-of-00004.safetensors",
|
97 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self.value.weight": "model-00004-of-00004.safetensors",
|
98 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
|
99 |
+
"language_heads.FR.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
|
100 |
+
"language_heads.FR.extra_transformer_layer_1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
|
101 |
+
"language_heads.FR.extra_transformer_layer_1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
|
102 |
+
"language_heads.FR.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
103 |
+
"language_heads.FR.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
104 |
+
"language_heads.FR.out_proj.bias": "model-00004-of-00004.safetensors",
|
105 |
+
"language_heads.FR.out_proj.weight": "model-00004-of-00004.safetensors",
|
106 |
+
"language_heads.HE.dense.bias": "model-00004-of-00004.safetensors",
|
107 |
+
"language_heads.HE.dense.weight": "model-00004-of-00004.safetensors",
|
108 |
+
"language_heads.HE.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
109 |
+
"language_heads.HE.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
110 |
+
"language_heads.HE.extra_transformer_layer_1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
|
111 |
+
"language_heads.HE.extra_transformer_layer_1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
|
112 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self.key.bias": "model-00004-of-00004.safetensors",
|
113 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self.key.weight": "model-00004-of-00004.safetensors",
|
114 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self.query.bias": "model-00004-of-00004.safetensors",
|
115 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self.query.weight": "model-00004-of-00004.safetensors",
|
116 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self.value.bias": "model-00004-of-00004.safetensors",
|
117 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self.value.weight": "model-00004-of-00004.safetensors",
|
118 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
|
119 |
+
"language_heads.HE.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
|
120 |
+
"language_heads.HE.extra_transformer_layer_1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
|
121 |
+
"language_heads.HE.extra_transformer_layer_1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
|
122 |
+
"language_heads.HE.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
123 |
+
"language_heads.HE.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
124 |
+
"language_heads.HE.out_proj.bias": "model-00004-of-00004.safetensors",
|
125 |
+
"language_heads.HE.out_proj.weight": "model-00004-of-00004.safetensors",
|
126 |
+
"language_heads.IT.dense.bias": "model-00004-of-00004.safetensors",
|
127 |
+
"language_heads.IT.dense.weight": "model-00004-of-00004.safetensors",
|
128 |
+
"language_heads.IT.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
129 |
+
"language_heads.IT.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
130 |
+
"language_heads.IT.extra_transformer_layer_1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
|
131 |
+
"language_heads.IT.extra_transformer_layer_1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
|
132 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self.key.bias": "model-00004-of-00004.safetensors",
|
133 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self.key.weight": "model-00004-of-00004.safetensors",
|
134 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self.query.bias": "model-00004-of-00004.safetensors",
|
135 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self.query.weight": "model-00004-of-00004.safetensors",
|
136 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self.value.bias": "model-00004-of-00004.safetensors",
|
137 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self.value.weight": "model-00004-of-00004.safetensors",
|
138 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
|
139 |
+
"language_heads.IT.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
|
140 |
+
"language_heads.IT.extra_transformer_layer_1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
|
141 |
+
"language_heads.IT.extra_transformer_layer_1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
|
142 |
+
"language_heads.IT.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
143 |
+
"language_heads.IT.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
144 |
+
"language_heads.IT.out_proj.bias": "model-00004-of-00004.safetensors",
|
145 |
+
"language_heads.IT.out_proj.weight": "model-00004-of-00004.safetensors",
|
146 |
+
"language_heads.NL.dense.bias": "model-00004-of-00004.safetensors",
|
147 |
+
"language_heads.NL.dense.weight": "model-00004-of-00004.safetensors",
|
148 |
+
"language_heads.NL.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
149 |
+
"language_heads.NL.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
150 |
+
"language_heads.NL.extra_transformer_layer_1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
|
151 |
+
"language_heads.NL.extra_transformer_layer_1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
|
152 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self.key.bias": "model-00004-of-00004.safetensors",
|
153 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self.key.weight": "model-00004-of-00004.safetensors",
|
154 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self.query.bias": "model-00004-of-00004.safetensors",
|
155 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self.query.weight": "model-00004-of-00004.safetensors",
|
156 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self.value.bias": "model-00004-of-00004.safetensors",
|
157 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self.value.weight": "model-00004-of-00004.safetensors",
|
158 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
|
159 |
+
"language_heads.NL.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
|
160 |
+
"language_heads.NL.extra_transformer_layer_1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
|
161 |
+
"language_heads.NL.extra_transformer_layer_1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
|
162 |
+
"language_heads.NL.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
163 |
+
"language_heads.NL.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
164 |
+
"language_heads.NL.out_proj.bias": "model-00004-of-00004.safetensors",
|
165 |
+
"language_heads.NL.out_proj.weight": "model-00004-of-00004.safetensors",
|
166 |
+
"language_heads.TR.dense.bias": "model-00004-of-00004.safetensors",
|
167 |
+
"language_heads.TR.dense.weight": "model-00004-of-00004.safetensors",
|
168 |
+
"language_heads.TR.extra_transformer_layer_1.LayerNorm.bias": "model-00004-of-00004.safetensors",
|
169 |
+
"language_heads.TR.extra_transformer_layer_1.LayerNorm.weight": "model-00004-of-00004.safetensors",
|
170 |
+
"language_heads.TR.extra_transformer_layer_1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
|
171 |
+
"language_heads.TR.extra_transformer_layer_1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
|
172 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self.key.bias": "model-00004-of-00004.safetensors",
|
173 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self.key.weight": "model-00004-of-00004.safetensors",
|
174 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self.query.bias": "model-00004-of-00004.safetensors",
|
175 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self.query.weight": "model-00004-of-00004.safetensors",
|
176 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self.value.bias": "model-00004-of-00004.safetensors",
|
177 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self.value.weight": "model-00004-of-00004.safetensors",
|
178 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
|
179 |
+
"language_heads.TR.extra_transformer_layer_1.attention.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
|
180 |
+
"language_heads.TR.extra_transformer_layer_1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
|
181 |
+
"language_heads.TR.extra_transformer_layer_1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
|
182 |
+
"language_heads.TR.extra_transformer_layer_1.output.dense.bias": "model-00004-of-00004.safetensors",
|
183 |
+
"language_heads.TR.extra_transformer_layer_1.output.dense.weight": "model-00004-of-00004.safetensors",
|
184 |
+
"language_heads.TR.out_proj.bias": "model-00004-of-00004.safetensors",
|
185 |
+
"language_heads.TR.out_proj.weight": "model-00004-of-00004.safetensors",
|
186 |
+
"roberta.embeddings.position_embeddings.weight": "model-00001-of-00004.safetensors",
|
187 |
+
"roberta.embeddings.token_type_embeddings.weight": "model-00001-of-00004.safetensors",
|
188 |
+
"roberta.embeddings.word_embeddings.weight": "model-00001-of-00004.safetensors",
|
189 |
+
"roberta.encoder.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
190 |
+
"roberta.encoder.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"roberta.encoder.layer.0.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
192 |
+
"roberta.encoder.layer.0.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
193 |
+
"roberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
194 |
+
"roberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
195 |
+
"roberta.encoder.layer.0.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
196 |
+
"roberta.encoder.layer.0.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
197 |
+
"roberta.encoder.layer.0.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
198 |
+
"roberta.encoder.layer.0.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
199 |
+
"roberta.encoder.layer.0.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
200 |
+
"roberta.encoder.layer.0.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
201 |
+
"roberta.encoder.layer.0.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
202 |
+
"roberta.encoder.layer.0.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
203 |
+
"roberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
204 |
+
"roberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
205 |
+
"roberta.encoder.layer.0.output.dense.bias": "model-00001-of-00004.safetensors",
|
206 |
+
"roberta.encoder.layer.0.output.dense.weight": "model-00001-of-00004.safetensors",
|
207 |
+
"roberta.encoder.layer.1.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
208 |
+
"roberta.encoder.layer.1.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
209 |
+
"roberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
210 |
+
"roberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
211 |
+
"roberta.encoder.layer.1.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
212 |
+
"roberta.encoder.layer.1.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
213 |
+
"roberta.encoder.layer.1.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
214 |
+
"roberta.encoder.layer.1.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
215 |
+
"roberta.encoder.layer.1.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
216 |
+
"roberta.encoder.layer.1.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"roberta.encoder.layer.1.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
218 |
+
"roberta.encoder.layer.1.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"roberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
220 |
+
"roberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"roberta.encoder.layer.1.output.dense.bias": "model-00001-of-00004.safetensors",
|
222 |
+
"roberta.encoder.layer.1.output.dense.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"roberta.encoder.layer.10.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
224 |
+
"roberta.encoder.layer.10.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
225 |
+
"roberta.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
226 |
+
"roberta.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
227 |
+
"roberta.encoder.layer.10.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
228 |
+
"roberta.encoder.layer.10.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
229 |
+
"roberta.encoder.layer.10.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
230 |
+
"roberta.encoder.layer.10.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
231 |
+
"roberta.encoder.layer.10.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
232 |
+
"roberta.encoder.layer.10.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
233 |
+
"roberta.encoder.layer.10.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
234 |
+
"roberta.encoder.layer.10.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
235 |
+
"roberta.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
236 |
+
"roberta.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
237 |
+
"roberta.encoder.layer.10.output.dense.bias": "model-00002-of-00004.safetensors",
|
238 |
+
"roberta.encoder.layer.10.output.dense.weight": "model-00002-of-00004.safetensors",
|
239 |
+
"roberta.encoder.layer.11.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
240 |
+
"roberta.encoder.layer.11.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
241 |
+
"roberta.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
242 |
+
"roberta.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
243 |
+
"roberta.encoder.layer.11.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
244 |
+
"roberta.encoder.layer.11.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
245 |
+
"roberta.encoder.layer.11.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
246 |
+
"roberta.encoder.layer.11.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
247 |
+
"roberta.encoder.layer.11.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
248 |
+
"roberta.encoder.layer.11.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
249 |
+
"roberta.encoder.layer.11.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
250 |
+
"roberta.encoder.layer.11.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
251 |
+
"roberta.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
252 |
+
"roberta.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
253 |
+
"roberta.encoder.layer.11.output.dense.bias": "model-00002-of-00004.safetensors",
|
254 |
+
"roberta.encoder.layer.11.output.dense.weight": "model-00002-of-00004.safetensors",
|
255 |
+
"roberta.encoder.layer.12.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
256 |
+
"roberta.encoder.layer.12.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
257 |
+
"roberta.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
258 |
+
"roberta.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
259 |
+
"roberta.encoder.layer.12.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
260 |
+
"roberta.encoder.layer.12.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
261 |
+
"roberta.encoder.layer.12.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
262 |
+
"roberta.encoder.layer.12.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
263 |
+
"roberta.encoder.layer.12.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
264 |
+
"roberta.encoder.layer.12.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
265 |
+
"roberta.encoder.layer.12.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
266 |
+
"roberta.encoder.layer.12.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
267 |
+
"roberta.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
268 |
+
"roberta.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
269 |
+
"roberta.encoder.layer.12.output.dense.bias": "model-00002-of-00004.safetensors",
|
270 |
+
"roberta.encoder.layer.12.output.dense.weight": "model-00002-of-00004.safetensors",
|
271 |
+
"roberta.encoder.layer.13.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
272 |
+
"roberta.encoder.layer.13.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
273 |
+
"roberta.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
274 |
+
"roberta.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
275 |
+
"roberta.encoder.layer.13.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
276 |
+
"roberta.encoder.layer.13.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
277 |
+
"roberta.encoder.layer.13.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
278 |
+
"roberta.encoder.layer.13.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
279 |
+
"roberta.encoder.layer.13.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
280 |
+
"roberta.encoder.layer.13.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
281 |
+
"roberta.encoder.layer.13.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
282 |
+
"roberta.encoder.layer.13.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
283 |
+
"roberta.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
284 |
+
"roberta.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
285 |
+
"roberta.encoder.layer.13.output.dense.bias": "model-00002-of-00004.safetensors",
|
286 |
+
"roberta.encoder.layer.13.output.dense.weight": "model-00002-of-00004.safetensors",
|
287 |
+
"roberta.encoder.layer.14.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
288 |
+
"roberta.encoder.layer.14.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
289 |
+
"roberta.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
290 |
+
"roberta.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
291 |
+
"roberta.encoder.layer.14.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
292 |
+
"roberta.encoder.layer.14.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
293 |
+
"roberta.encoder.layer.14.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
294 |
+
"roberta.encoder.layer.14.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
295 |
+
"roberta.encoder.layer.14.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
296 |
+
"roberta.encoder.layer.14.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
297 |
+
"roberta.encoder.layer.14.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
298 |
+
"roberta.encoder.layer.14.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
299 |
+
"roberta.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
300 |
+
"roberta.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
301 |
+
"roberta.encoder.layer.14.output.dense.bias": "model-00002-of-00004.safetensors",
|
302 |
+
"roberta.encoder.layer.14.output.dense.weight": "model-00002-of-00004.safetensors",
|
303 |
+
"roberta.encoder.layer.15.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
304 |
+
"roberta.encoder.layer.15.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
305 |
+
"roberta.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
306 |
+
"roberta.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
307 |
+
"roberta.encoder.layer.15.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
308 |
+
"roberta.encoder.layer.15.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
309 |
+
"roberta.encoder.layer.15.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
310 |
+
"roberta.encoder.layer.15.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
311 |
+
"roberta.encoder.layer.15.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
312 |
+
"roberta.encoder.layer.15.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
313 |
+
"roberta.encoder.layer.15.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
314 |
+
"roberta.encoder.layer.15.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
315 |
+
"roberta.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
316 |
+
"roberta.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
317 |
+
"roberta.encoder.layer.15.output.dense.bias": "model-00002-of-00004.safetensors",
|
318 |
+
"roberta.encoder.layer.15.output.dense.weight": "model-00002-of-00004.safetensors",
|
319 |
+
"roberta.encoder.layer.16.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
320 |
+
"roberta.encoder.layer.16.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
321 |
+
"roberta.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
322 |
+
"roberta.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
323 |
+
"roberta.encoder.layer.16.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
324 |
+
"roberta.encoder.layer.16.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
325 |
+
"roberta.encoder.layer.16.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
326 |
+
"roberta.encoder.layer.16.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
327 |
+
"roberta.encoder.layer.16.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
328 |
+
"roberta.encoder.layer.16.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
329 |
+
"roberta.encoder.layer.16.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
330 |
+
"roberta.encoder.layer.16.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
331 |
+
"roberta.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
332 |
+
"roberta.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
333 |
+
"roberta.encoder.layer.16.output.dense.bias": "model-00002-of-00004.safetensors",
|
334 |
+
"roberta.encoder.layer.16.output.dense.weight": "model-00002-of-00004.safetensors",
|
335 |
+
"roberta.encoder.layer.17.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
336 |
+
"roberta.encoder.layer.17.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
337 |
+
"roberta.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
338 |
+
"roberta.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
339 |
+
"roberta.encoder.layer.17.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
340 |
+
"roberta.encoder.layer.17.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
341 |
+
"roberta.encoder.layer.17.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
342 |
+
"roberta.encoder.layer.17.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
343 |
+
"roberta.encoder.layer.17.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
344 |
+
"roberta.encoder.layer.17.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
345 |
+
"roberta.encoder.layer.17.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
346 |
+
"roberta.encoder.layer.17.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
347 |
+
"roberta.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
348 |
+
"roberta.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
349 |
+
"roberta.encoder.layer.17.output.dense.bias": "model-00002-of-00004.safetensors",
|
350 |
+
"roberta.encoder.layer.17.output.dense.weight": "model-00002-of-00004.safetensors",
|
351 |
+
"roberta.encoder.layer.18.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
352 |
+
"roberta.encoder.layer.18.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
353 |
+
"roberta.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
354 |
+
"roberta.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
355 |
+
"roberta.encoder.layer.18.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
356 |
+
"roberta.encoder.layer.18.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
357 |
+
"roberta.encoder.layer.18.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
358 |
+
"roberta.encoder.layer.18.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
359 |
+
"roberta.encoder.layer.18.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
360 |
+
"roberta.encoder.layer.18.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
361 |
+
"roberta.encoder.layer.18.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
362 |
+
"roberta.encoder.layer.18.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
363 |
+
"roberta.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
364 |
+
"roberta.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
365 |
+
"roberta.encoder.layer.18.output.dense.bias": "model-00002-of-00004.safetensors",
|
366 |
+
"roberta.encoder.layer.18.output.dense.weight": "model-00002-of-00004.safetensors",
|
367 |
+
"roberta.encoder.layer.19.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
368 |
+
"roberta.encoder.layer.19.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
369 |
+
"roberta.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
370 |
+
"roberta.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
371 |
+
"roberta.encoder.layer.19.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
372 |
+
"roberta.encoder.layer.19.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
373 |
+
"roberta.encoder.layer.19.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
374 |
+
"roberta.encoder.layer.19.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
375 |
+
"roberta.encoder.layer.19.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
376 |
+
"roberta.encoder.layer.19.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
377 |
+
"roberta.encoder.layer.19.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
378 |
+
"roberta.encoder.layer.19.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
379 |
+
"roberta.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
380 |
+
"roberta.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
381 |
+
"roberta.encoder.layer.19.output.dense.bias": "model-00002-of-00004.safetensors",
|
382 |
+
"roberta.encoder.layer.19.output.dense.weight": "model-00002-of-00004.safetensors",
|
383 |
+
"roberta.encoder.layer.2.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
384 |
+
"roberta.encoder.layer.2.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
385 |
+
"roberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
386 |
+
"roberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
387 |
+
"roberta.encoder.layer.2.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
388 |
+
"roberta.encoder.layer.2.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
389 |
+
"roberta.encoder.layer.2.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
390 |
+
"roberta.encoder.layer.2.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
391 |
+
"roberta.encoder.layer.2.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
392 |
+
"roberta.encoder.layer.2.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
393 |
+
"roberta.encoder.layer.2.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
394 |
+
"roberta.encoder.layer.2.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
395 |
+
"roberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
396 |
+
"roberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
397 |
+
"roberta.encoder.layer.2.output.dense.bias": "model-00001-of-00004.safetensors",
|
398 |
+
"roberta.encoder.layer.2.output.dense.weight": "model-00001-of-00004.safetensors",
|
399 |
+
"roberta.encoder.layer.20.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
400 |
+
"roberta.encoder.layer.20.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
401 |
+
"roberta.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
402 |
+
"roberta.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
403 |
+
"roberta.encoder.layer.20.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
404 |
+
"roberta.encoder.layer.20.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
405 |
+
"roberta.encoder.layer.20.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
406 |
+
"roberta.encoder.layer.20.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
407 |
+
"roberta.encoder.layer.20.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
408 |
+
"roberta.encoder.layer.20.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
409 |
+
"roberta.encoder.layer.20.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
410 |
+
"roberta.encoder.layer.20.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
411 |
+
"roberta.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
412 |
+
"roberta.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
413 |
+
"roberta.encoder.layer.20.output.dense.bias": "model-00002-of-00004.safetensors",
|
414 |
+
"roberta.encoder.layer.20.output.dense.weight": "model-00002-of-00004.safetensors",
|
415 |
+
"roberta.encoder.layer.21.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
416 |
+
"roberta.encoder.layer.21.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
417 |
+
"roberta.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
418 |
+
"roberta.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
419 |
+
"roberta.encoder.layer.21.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
420 |
+
"roberta.encoder.layer.21.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
421 |
+
"roberta.encoder.layer.21.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
422 |
+
"roberta.encoder.layer.21.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
423 |
+
"roberta.encoder.layer.21.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
424 |
+
"roberta.encoder.layer.21.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
425 |
+
"roberta.encoder.layer.21.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
426 |
+
"roberta.encoder.layer.21.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
427 |
+
"roberta.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
428 |
+
"roberta.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
429 |
+
"roberta.encoder.layer.21.output.dense.bias": "model-00002-of-00004.safetensors",
|
430 |
+
"roberta.encoder.layer.21.output.dense.weight": "model-00002-of-00004.safetensors",
|
431 |
+
"roberta.encoder.layer.22.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
432 |
+
"roberta.encoder.layer.22.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
433 |
+
"roberta.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
434 |
+
"roberta.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
435 |
+
"roberta.encoder.layer.22.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
436 |
+
"roberta.encoder.layer.22.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
437 |
+
"roberta.encoder.layer.22.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
438 |
+
"roberta.encoder.layer.22.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
439 |
+
"roberta.encoder.layer.22.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
440 |
+
"roberta.encoder.layer.22.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
441 |
+
"roberta.encoder.layer.22.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
442 |
+
"roberta.encoder.layer.22.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
443 |
+
"roberta.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
444 |
+
"roberta.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
445 |
+
"roberta.encoder.layer.22.output.dense.bias": "model-00002-of-00004.safetensors",
|
446 |
+
"roberta.encoder.layer.22.output.dense.weight": "model-00002-of-00004.safetensors",
|
447 |
+
"roberta.encoder.layer.23.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
448 |
+
"roberta.encoder.layer.23.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
449 |
+
"roberta.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
450 |
+
"roberta.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
451 |
+
"roberta.encoder.layer.23.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
452 |
+
"roberta.encoder.layer.23.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
453 |
+
"roberta.encoder.layer.23.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
454 |
+
"roberta.encoder.layer.23.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
455 |
+
"roberta.encoder.layer.23.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
456 |
+
"roberta.encoder.layer.23.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
457 |
+
"roberta.encoder.layer.23.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
458 |
+
"roberta.encoder.layer.23.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
459 |
+
"roberta.encoder.layer.23.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
460 |
+
"roberta.encoder.layer.23.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
461 |
+
"roberta.encoder.layer.23.output.dense.bias": "model-00003-of-00004.safetensors",
|
462 |
+
"roberta.encoder.layer.23.output.dense.weight": "model-00003-of-00004.safetensors",
|
463 |
+
"roberta.encoder.layer.24.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
464 |
+
"roberta.encoder.layer.24.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
465 |
+
"roberta.encoder.layer.24.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
466 |
+
"roberta.encoder.layer.24.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
467 |
+
"roberta.encoder.layer.24.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
468 |
+
"roberta.encoder.layer.24.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
469 |
+
"roberta.encoder.layer.24.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
470 |
+
"roberta.encoder.layer.24.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
471 |
+
"roberta.encoder.layer.24.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
472 |
+
"roberta.encoder.layer.24.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
473 |
+
"roberta.encoder.layer.24.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
474 |
+
"roberta.encoder.layer.24.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
475 |
+
"roberta.encoder.layer.24.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
476 |
+
"roberta.encoder.layer.24.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
477 |
+
"roberta.encoder.layer.24.output.dense.bias": "model-00003-of-00004.safetensors",
|
478 |
+
"roberta.encoder.layer.24.output.dense.weight": "model-00003-of-00004.safetensors",
|
479 |
+
"roberta.encoder.layer.25.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
480 |
+
"roberta.encoder.layer.25.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
481 |
+
"roberta.encoder.layer.25.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
482 |
+
"roberta.encoder.layer.25.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
483 |
+
"roberta.encoder.layer.25.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
484 |
+
"roberta.encoder.layer.25.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
485 |
+
"roberta.encoder.layer.25.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
486 |
+
"roberta.encoder.layer.25.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
487 |
+
"roberta.encoder.layer.25.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
488 |
+
"roberta.encoder.layer.25.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
489 |
+
"roberta.encoder.layer.25.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
490 |
+
"roberta.encoder.layer.25.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
491 |
+
"roberta.encoder.layer.25.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
492 |
+
"roberta.encoder.layer.25.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
493 |
+
"roberta.encoder.layer.25.output.dense.bias": "model-00003-of-00004.safetensors",
|
494 |
+
"roberta.encoder.layer.25.output.dense.weight": "model-00003-of-00004.safetensors",
|
495 |
+
"roberta.encoder.layer.26.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
496 |
+
"roberta.encoder.layer.26.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
497 |
+
"roberta.encoder.layer.26.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
498 |
+
"roberta.encoder.layer.26.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
499 |
+
"roberta.encoder.layer.26.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
500 |
+
"roberta.encoder.layer.26.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
501 |
+
"roberta.encoder.layer.26.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
502 |
+
"roberta.encoder.layer.26.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
503 |
+
"roberta.encoder.layer.26.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
504 |
+
"roberta.encoder.layer.26.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
505 |
+
"roberta.encoder.layer.26.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
506 |
+
"roberta.encoder.layer.26.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
507 |
+
"roberta.encoder.layer.26.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
508 |
+
"roberta.encoder.layer.26.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
509 |
+
"roberta.encoder.layer.26.output.dense.bias": "model-00003-of-00004.safetensors",
|
510 |
+
"roberta.encoder.layer.26.output.dense.weight": "model-00003-of-00004.safetensors",
|
511 |
+
"roberta.encoder.layer.27.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
512 |
+
"roberta.encoder.layer.27.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
513 |
+
"roberta.encoder.layer.27.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
514 |
+
"roberta.encoder.layer.27.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
515 |
+
"roberta.encoder.layer.27.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
516 |
+
"roberta.encoder.layer.27.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
517 |
+
"roberta.encoder.layer.27.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
518 |
+
"roberta.encoder.layer.27.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
519 |
+
"roberta.encoder.layer.27.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
520 |
+
"roberta.encoder.layer.27.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
521 |
+
"roberta.encoder.layer.27.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
522 |
+
"roberta.encoder.layer.27.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
523 |
+
"roberta.encoder.layer.27.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
524 |
+
"roberta.encoder.layer.27.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
525 |
+
"roberta.encoder.layer.27.output.dense.bias": "model-00003-of-00004.safetensors",
|
526 |
+
"roberta.encoder.layer.27.output.dense.weight": "model-00003-of-00004.safetensors",
|
527 |
+
"roberta.encoder.layer.28.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
528 |
+
"roberta.encoder.layer.28.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
529 |
+
"roberta.encoder.layer.28.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
530 |
+
"roberta.encoder.layer.28.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
531 |
+
"roberta.encoder.layer.28.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
532 |
+
"roberta.encoder.layer.28.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
533 |
+
"roberta.encoder.layer.28.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
534 |
+
"roberta.encoder.layer.28.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
535 |
+
"roberta.encoder.layer.28.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
536 |
+
"roberta.encoder.layer.28.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
537 |
+
"roberta.encoder.layer.28.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
538 |
+
"roberta.encoder.layer.28.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
539 |
+
"roberta.encoder.layer.28.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
540 |
+
"roberta.encoder.layer.28.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
541 |
+
"roberta.encoder.layer.28.output.dense.bias": "model-00003-of-00004.safetensors",
|
542 |
+
"roberta.encoder.layer.28.output.dense.weight": "model-00003-of-00004.safetensors",
|
543 |
+
"roberta.encoder.layer.29.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
544 |
+
"roberta.encoder.layer.29.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
545 |
+
"roberta.encoder.layer.29.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
546 |
+
"roberta.encoder.layer.29.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
547 |
+
"roberta.encoder.layer.29.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
548 |
+
"roberta.encoder.layer.29.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
549 |
+
"roberta.encoder.layer.29.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
550 |
+
"roberta.encoder.layer.29.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
551 |
+
"roberta.encoder.layer.29.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
552 |
+
"roberta.encoder.layer.29.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
553 |
+
"roberta.encoder.layer.29.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
554 |
+
"roberta.encoder.layer.29.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
555 |
+
"roberta.encoder.layer.29.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
556 |
+
"roberta.encoder.layer.29.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
557 |
+
"roberta.encoder.layer.29.output.dense.bias": "model-00003-of-00004.safetensors",
|
558 |
+
"roberta.encoder.layer.29.output.dense.weight": "model-00003-of-00004.safetensors",
|
559 |
+
"roberta.encoder.layer.3.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
560 |
+
"roberta.encoder.layer.3.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
561 |
+
"roberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
562 |
+
"roberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
563 |
+
"roberta.encoder.layer.3.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
564 |
+
"roberta.encoder.layer.3.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
565 |
+
"roberta.encoder.layer.3.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
566 |
+
"roberta.encoder.layer.3.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
567 |
+
"roberta.encoder.layer.3.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
568 |
+
"roberta.encoder.layer.3.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
569 |
+
"roberta.encoder.layer.3.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
570 |
+
"roberta.encoder.layer.3.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
571 |
+
"roberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
572 |
+
"roberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
573 |
+
"roberta.encoder.layer.3.output.dense.bias": "model-00001-of-00004.safetensors",
|
574 |
+
"roberta.encoder.layer.3.output.dense.weight": "model-00001-of-00004.safetensors",
|
575 |
+
"roberta.encoder.layer.30.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
576 |
+
"roberta.encoder.layer.30.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
577 |
+
"roberta.encoder.layer.30.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
578 |
+
"roberta.encoder.layer.30.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
579 |
+
"roberta.encoder.layer.30.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
580 |
+
"roberta.encoder.layer.30.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
581 |
+
"roberta.encoder.layer.30.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
582 |
+
"roberta.encoder.layer.30.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
583 |
+
"roberta.encoder.layer.30.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
584 |
+
"roberta.encoder.layer.30.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
585 |
+
"roberta.encoder.layer.30.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
586 |
+
"roberta.encoder.layer.30.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
587 |
+
"roberta.encoder.layer.30.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
588 |
+
"roberta.encoder.layer.30.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
589 |
+
"roberta.encoder.layer.30.output.dense.bias": "model-00003-of-00004.safetensors",
|
590 |
+
"roberta.encoder.layer.30.output.dense.weight": "model-00003-of-00004.safetensors",
|
591 |
+
"roberta.encoder.layer.31.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
592 |
+
"roberta.encoder.layer.31.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
593 |
+
"roberta.encoder.layer.31.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
594 |
+
"roberta.encoder.layer.31.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
595 |
+
"roberta.encoder.layer.31.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
596 |
+
"roberta.encoder.layer.31.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
597 |
+
"roberta.encoder.layer.31.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
598 |
+
"roberta.encoder.layer.31.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
599 |
+
"roberta.encoder.layer.31.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
600 |
+
"roberta.encoder.layer.31.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
601 |
+
"roberta.encoder.layer.31.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
602 |
+
"roberta.encoder.layer.31.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
603 |
+
"roberta.encoder.layer.31.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
604 |
+
"roberta.encoder.layer.31.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
605 |
+
"roberta.encoder.layer.31.output.dense.bias": "model-00003-of-00004.safetensors",
|
606 |
+
"roberta.encoder.layer.31.output.dense.weight": "model-00003-of-00004.safetensors",
|
607 |
+
"roberta.encoder.layer.32.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
608 |
+
"roberta.encoder.layer.32.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
609 |
+
"roberta.encoder.layer.32.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
610 |
+
"roberta.encoder.layer.32.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
611 |
+
"roberta.encoder.layer.32.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
612 |
+
"roberta.encoder.layer.32.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
613 |
+
"roberta.encoder.layer.32.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
614 |
+
"roberta.encoder.layer.32.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
615 |
+
"roberta.encoder.layer.32.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
616 |
+
"roberta.encoder.layer.32.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
617 |
+
"roberta.encoder.layer.32.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
618 |
+
"roberta.encoder.layer.32.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
619 |
+
"roberta.encoder.layer.32.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
620 |
+
"roberta.encoder.layer.32.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
621 |
+
"roberta.encoder.layer.32.output.dense.bias": "model-00003-of-00004.safetensors",
|
622 |
+
"roberta.encoder.layer.32.output.dense.weight": "model-00003-of-00004.safetensors",
|
623 |
+
"roberta.encoder.layer.33.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
624 |
+
"roberta.encoder.layer.33.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
625 |
+
"roberta.encoder.layer.33.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
626 |
+
"roberta.encoder.layer.33.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
627 |
+
"roberta.encoder.layer.33.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
628 |
+
"roberta.encoder.layer.33.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
629 |
+
"roberta.encoder.layer.33.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
630 |
+
"roberta.encoder.layer.33.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
631 |
+
"roberta.encoder.layer.33.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
632 |
+
"roberta.encoder.layer.33.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
633 |
+
"roberta.encoder.layer.33.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
634 |
+
"roberta.encoder.layer.33.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
635 |
+
"roberta.encoder.layer.33.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
636 |
+
"roberta.encoder.layer.33.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
637 |
+
"roberta.encoder.layer.33.output.dense.bias": "model-00003-of-00004.safetensors",
|
638 |
+
"roberta.encoder.layer.33.output.dense.weight": "model-00003-of-00004.safetensors",
|
639 |
+
"roberta.encoder.layer.34.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
640 |
+
"roberta.encoder.layer.34.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
641 |
+
"roberta.encoder.layer.34.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
642 |
+
"roberta.encoder.layer.34.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
643 |
+
"roberta.encoder.layer.34.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
644 |
+
"roberta.encoder.layer.34.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
645 |
+
"roberta.encoder.layer.34.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
646 |
+
"roberta.encoder.layer.34.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
647 |
+
"roberta.encoder.layer.34.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
648 |
+
"roberta.encoder.layer.34.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
649 |
+
"roberta.encoder.layer.34.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
650 |
+
"roberta.encoder.layer.34.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
651 |
+
"roberta.encoder.layer.34.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
652 |
+
"roberta.encoder.layer.34.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
653 |
+
"roberta.encoder.layer.34.output.dense.bias": "model-00003-of-00004.safetensors",
|
654 |
+
"roberta.encoder.layer.34.output.dense.weight": "model-00003-of-00004.safetensors",
|
655 |
+
"roberta.encoder.layer.35.LayerNorm.bias": "model-00003-of-00004.safetensors",
|
656 |
+
"roberta.encoder.layer.35.LayerNorm.weight": "model-00003-of-00004.safetensors",
|
657 |
+
"roberta.encoder.layer.35.attention.output.dense.bias": "model-00003-of-00004.safetensors",
|
658 |
+
"roberta.encoder.layer.35.attention.output.dense.weight": "model-00003-of-00004.safetensors",
|
659 |
+
"roberta.encoder.layer.35.attention.self.key.bias": "model-00003-of-00004.safetensors",
|
660 |
+
"roberta.encoder.layer.35.attention.self.key.weight": "model-00003-of-00004.safetensors",
|
661 |
+
"roberta.encoder.layer.35.attention.self.query.bias": "model-00003-of-00004.safetensors",
|
662 |
+
"roberta.encoder.layer.35.attention.self.query.weight": "model-00003-of-00004.safetensors",
|
663 |
+
"roberta.encoder.layer.35.attention.self.value.bias": "model-00003-of-00004.safetensors",
|
664 |
+
"roberta.encoder.layer.35.attention.self.value.weight": "model-00003-of-00004.safetensors",
|
665 |
+
"roberta.encoder.layer.35.attention.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors",
|
666 |
+
"roberta.encoder.layer.35.attention.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors",
|
667 |
+
"roberta.encoder.layer.35.intermediate.dense.bias": "model-00003-of-00004.safetensors",
|
668 |
+
"roberta.encoder.layer.35.intermediate.dense.weight": "model-00003-of-00004.safetensors",
|
669 |
+
"roberta.encoder.layer.35.output.dense.bias": "model-00003-of-00004.safetensors",
|
670 |
+
"roberta.encoder.layer.35.output.dense.weight": "model-00003-of-00004.safetensors",
|
671 |
+
"roberta.encoder.layer.4.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
672 |
+
"roberta.encoder.layer.4.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
673 |
+
"roberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
674 |
+
"roberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
675 |
+
"roberta.encoder.layer.4.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
676 |
+
"roberta.encoder.layer.4.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
677 |
+
"roberta.encoder.layer.4.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
678 |
+
"roberta.encoder.layer.4.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
679 |
+
"roberta.encoder.layer.4.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
680 |
+
"roberta.encoder.layer.4.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
681 |
+
"roberta.encoder.layer.4.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
682 |
+
"roberta.encoder.layer.4.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
683 |
+
"roberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
684 |
+
"roberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
685 |
+
"roberta.encoder.layer.4.output.dense.bias": "model-00001-of-00004.safetensors",
|
686 |
+
"roberta.encoder.layer.4.output.dense.weight": "model-00001-of-00004.safetensors",
|
687 |
+
"roberta.encoder.layer.5.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
688 |
+
"roberta.encoder.layer.5.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
689 |
+
"roberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
690 |
+
"roberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
691 |
+
"roberta.encoder.layer.5.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
692 |
+
"roberta.encoder.layer.5.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
693 |
+
"roberta.encoder.layer.5.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
694 |
+
"roberta.encoder.layer.5.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
695 |
+
"roberta.encoder.layer.5.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
696 |
+
"roberta.encoder.layer.5.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
697 |
+
"roberta.encoder.layer.5.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
698 |
+
"roberta.encoder.layer.5.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
699 |
+
"roberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
700 |
+
"roberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
701 |
+
"roberta.encoder.layer.5.output.dense.bias": "model-00001-of-00004.safetensors",
|
702 |
+
"roberta.encoder.layer.5.output.dense.weight": "model-00001-of-00004.safetensors",
|
703 |
+
"roberta.encoder.layer.6.LayerNorm.bias": "model-00001-of-00004.safetensors",
|
704 |
+
"roberta.encoder.layer.6.LayerNorm.weight": "model-00001-of-00004.safetensors",
|
705 |
+
"roberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
706 |
+
"roberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
707 |
+
"roberta.encoder.layer.6.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
708 |
+
"roberta.encoder.layer.6.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
709 |
+
"roberta.encoder.layer.6.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
710 |
+
"roberta.encoder.layer.6.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
711 |
+
"roberta.encoder.layer.6.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
712 |
+
"roberta.encoder.layer.6.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
713 |
+
"roberta.encoder.layer.6.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
714 |
+
"roberta.encoder.layer.6.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
715 |
+
"roberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
716 |
+
"roberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
717 |
+
"roberta.encoder.layer.6.output.dense.bias": "model-00001-of-00004.safetensors",
|
718 |
+
"roberta.encoder.layer.6.output.dense.weight": "model-00001-of-00004.safetensors",
|
719 |
+
"roberta.encoder.layer.7.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
720 |
+
"roberta.encoder.layer.7.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
721 |
+
"roberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00004.safetensors",
|
722 |
+
"roberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00004.safetensors",
|
723 |
+
"roberta.encoder.layer.7.attention.self.key.bias": "model-00001-of-00004.safetensors",
|
724 |
+
"roberta.encoder.layer.7.attention.self.key.weight": "model-00001-of-00004.safetensors",
|
725 |
+
"roberta.encoder.layer.7.attention.self.query.bias": "model-00001-of-00004.safetensors",
|
726 |
+
"roberta.encoder.layer.7.attention.self.query.weight": "model-00001-of-00004.safetensors",
|
727 |
+
"roberta.encoder.layer.7.attention.self.value.bias": "model-00001-of-00004.safetensors",
|
728 |
+
"roberta.encoder.layer.7.attention.self.value.weight": "model-00001-of-00004.safetensors",
|
729 |
+
"roberta.encoder.layer.7.attention.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
730 |
+
"roberta.encoder.layer.7.attention.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
731 |
+
"roberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00004.safetensors",
|
732 |
+
"roberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00004.safetensors",
|
733 |
+
"roberta.encoder.layer.7.output.dense.bias": "model-00002-of-00004.safetensors",
|
734 |
+
"roberta.encoder.layer.7.output.dense.weight": "model-00002-of-00004.safetensors",
|
735 |
+
"roberta.encoder.layer.8.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
736 |
+
"roberta.encoder.layer.8.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
737 |
+
"roberta.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
738 |
+
"roberta.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
739 |
+
"roberta.encoder.layer.8.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
740 |
+
"roberta.encoder.layer.8.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
741 |
+
"roberta.encoder.layer.8.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
742 |
+
"roberta.encoder.layer.8.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
743 |
+
"roberta.encoder.layer.8.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
744 |
+
"roberta.encoder.layer.8.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
745 |
+
"roberta.encoder.layer.8.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
746 |
+
"roberta.encoder.layer.8.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
747 |
+
"roberta.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
748 |
+
"roberta.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
749 |
+
"roberta.encoder.layer.8.output.dense.bias": "model-00002-of-00004.safetensors",
|
750 |
+
"roberta.encoder.layer.8.output.dense.weight": "model-00002-of-00004.safetensors",
|
751 |
+
"roberta.encoder.layer.9.LayerNorm.bias": "model-00002-of-00004.safetensors",
|
752 |
+
"roberta.encoder.layer.9.LayerNorm.weight": "model-00002-of-00004.safetensors",
|
753 |
+
"roberta.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00004.safetensors",
|
754 |
+
"roberta.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00004.safetensors",
|
755 |
+
"roberta.encoder.layer.9.attention.self.key.bias": "model-00002-of-00004.safetensors",
|
756 |
+
"roberta.encoder.layer.9.attention.self.key.weight": "model-00002-of-00004.safetensors",
|
757 |
+
"roberta.encoder.layer.9.attention.self.query.bias": "model-00002-of-00004.safetensors",
|
758 |
+
"roberta.encoder.layer.9.attention.self.query.weight": "model-00002-of-00004.safetensors",
|
759 |
+
"roberta.encoder.layer.9.attention.self.value.bias": "model-00002-of-00004.safetensors",
|
760 |
+
"roberta.encoder.layer.9.attention.self.value.weight": "model-00002-of-00004.safetensors",
|
761 |
+
"roberta.encoder.layer.9.attention.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors",
|
762 |
+
"roberta.encoder.layer.9.attention.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors",
|
763 |
+
"roberta.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00004.safetensors",
|
764 |
+
"roberta.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00004.safetensors",
|
765 |
+
"roberta.encoder.layer.9.output.dense.bias": "model-00002-of-00004.safetensors",
|
766 |
+
"roberta.encoder.layer.9.output.dense.weight": "model-00002-of-00004.safetensors",
|
767 |
+
"roberta.pooler.dense.bias": "model-00003-of-00004.safetensors",
|
768 |
+
"roberta.pooler.dense.weight": "model-00003-of-00004.safetensors"
|
769 |
+
}
|
770 |
+
}
|