Hugging Face's logo

Lightricks
/
T5-XXL-8bit

Transformers
Safetensors
t5
text-generation-inference
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Community
nisan commited on
Commit
0572ec9
•
1 Parent(s): 923bb91

Upload model

Browse files
Files changed (4) hide show
  1. config.json +44 -0
  2. model-00001-of-00002.safetensors +3 -0
  3. model-00002-of-00002.safetensors +3 -0
  4. model.safetensors.index.json +370 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/models/PixArt-alpha/PixArt-XL-2-1024-MS",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "quantization_config": {
26
+ "bnb_4bit_compute_dtype": "float32",
27
+ "bnb_4bit_quant_type": "fp4",
28
+ "bnb_4bit_use_double_quant": false,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": false,
34
+ "load_in_8bit": true,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "relative_attention_max_distance": 128,
38
+ "relative_attention_num_buckets": 32,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.36.2",
42
+ "use_cache": true,
43
+ "vocab_size": 32128
44
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e9064f48ab1cdc83750e627c4ff9ebc9eb1c957d11922a72d01398344cfabc
3
+ size 4997717392
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e3fbd831c318c4775a4e6941b08e0bbe25e76ae972da8d9138ed6551207d27
3
+ size 906607152
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5904281600
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
16
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
17
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
18
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
19
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
20
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
21
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
22
+ "encoder.block.1.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
23
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
24
+ "encoder.block.1.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
25
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
26
+ "encoder.block.1.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
27
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
28
+ "encoder.block.1.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
29
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
30
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
31
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
32
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
33
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
34
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
35
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
36
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
37
+ "encoder.block.10.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
38
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
39
+ "encoder.block.10.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
40
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
41
+ "encoder.block.10.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
42
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
43
+ "encoder.block.10.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
44
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
45
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
46
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
47
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
48
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
49
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
50
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
51
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
52
+ "encoder.block.11.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
53
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
54
+ "encoder.block.11.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
55
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
56
+ "encoder.block.11.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
57
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
58
+ "encoder.block.11.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
59
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
60
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
61
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
62
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
63
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
64
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
65
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
66
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
67
+ "encoder.block.12.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
68
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
69
+ "encoder.block.12.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
70
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
71
+ "encoder.block.12.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
72
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
73
+ "encoder.block.12.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
74
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
75
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
76
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
77
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
78
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
79
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
80
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
81
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
82
+ "encoder.block.13.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
83
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
84
+ "encoder.block.13.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
85
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
86
+ "encoder.block.13.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
87
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
88
+ "encoder.block.13.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
89
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
90
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
91
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
92
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
93
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
94
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
95
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
96
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
97
+ "encoder.block.14.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
98
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
99
+ "encoder.block.14.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
100
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
101
+ "encoder.block.14.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
102
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
103
+ "encoder.block.14.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
104
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
105
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
106
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
107
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
108
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
109
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
110
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
111
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
112
+ "encoder.block.15.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
113
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
114
+ "encoder.block.15.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
115
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
116
+ "encoder.block.15.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
117
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
118
+ "encoder.block.15.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
119
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
120
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
121
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
122
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
123
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
124
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
125
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
126
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
127
+ "encoder.block.16.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
128
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
129
+ "encoder.block.16.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
130
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
131
+ "encoder.block.16.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
132
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
133
+ "encoder.block.16.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
134
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
135
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
136
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
137
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
138
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
139
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
140
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
141
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
142
+ "encoder.block.17.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
143
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
144
+ "encoder.block.17.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
145
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
146
+ "encoder.block.17.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
147
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
148
+ "encoder.block.17.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
149
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
150
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
151
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
152
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
153
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
154
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
155
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
156
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
157
+ "encoder.block.18.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
158
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
159
+ "encoder.block.18.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
160
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
161
+ "encoder.block.18.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
162
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
163
+ "encoder.block.18.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
164
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
165
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
166
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
167
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
168
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
169
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
170
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
171
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
172
+ "encoder.block.19.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
173
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
174
+ "encoder.block.19.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
175
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
176
+ "encoder.block.19.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
177
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
178
+ "encoder.block.19.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
179
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
180
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
181
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
182
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
183
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
184
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
185
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
186
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
187
+ "encoder.block.2.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
188
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
189
+ "encoder.block.2.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
190
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
191
+ "encoder.block.2.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
192
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
193
+ "encoder.block.2.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
194
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
195
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
196
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
197
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
198
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
199
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
200
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
201
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
202
+ "encoder.block.20.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
203
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
204
+ "encoder.block.20.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
205
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
206
+ "encoder.block.20.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
207
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
208
+ "encoder.block.20.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
209
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
210
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
211
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
212
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
213
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
214
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
215
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
216
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
217
+ "encoder.block.21.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
218
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
219
+ "encoder.block.21.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
220
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
221
+ "encoder.block.21.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
222
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
223
+ "encoder.block.21.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
224
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
225
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
226
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
227
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
228
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
229
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
230
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
231
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
232
+ "encoder.block.22.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
233
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
234
+ "encoder.block.22.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
235
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
236
+ "encoder.block.22.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
237
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
238
+ "encoder.block.22.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
239
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
240
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
241
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
242
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
243
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
244
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
245
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
246
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
247
+ "encoder.block.23.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
248
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
249
+ "encoder.block.23.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
250
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
251
+ "encoder.block.23.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
252
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
253
+ "encoder.block.23.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
254
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
255
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
256
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
257
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
258
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
259
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
260
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
261
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
262
+ "encoder.block.3.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
263
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
264
+ "encoder.block.3.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
265
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
266
+ "encoder.block.3.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
267
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
268
+ "encoder.block.3.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
269
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
270
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
271
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
272
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
273
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
274
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
275
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
276
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
277
+ "encoder.block.4.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
278
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
279
+ "encoder.block.4.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
280
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
281
+ "encoder.block.4.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
282
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
283
+ "encoder.block.4.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
284
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
285
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
286
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
287
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
288
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
289
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
290
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
291
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
292
+ "encoder.block.5.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
293
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
294
+ "encoder.block.5.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
295
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
296
+ "encoder.block.5.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
297
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
298
+ "encoder.block.5.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
299
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
300
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
301
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
302
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
303
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
304
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
305
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
306
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
307
+ "encoder.block.6.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
308
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
309
+ "encoder.block.6.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
310
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
311
+ "encoder.block.6.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
312
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
313
+ "encoder.block.6.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
314
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
315
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
316
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
317
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
318
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
319
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
320
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
321
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
322
+ "encoder.block.7.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
323
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
324
+ "encoder.block.7.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
325
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
326
+ "encoder.block.7.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
327
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
328
+ "encoder.block.7.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
329
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
330
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
331
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
332
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
333
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
334
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
335
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
336
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
337
+ "encoder.block.8.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
338
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
339
+ "encoder.block.8.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
340
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
341
+ "encoder.block.8.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
342
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
343
+ "encoder.block.8.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
344
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
345
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
346
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
347
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
348
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
349
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
350
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
351
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
352
+ "encoder.block.9.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
353
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
354
+ "encoder.block.9.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
355
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
356
+ "encoder.block.9.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
357
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
358
+ "encoder.block.9.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
359
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
360
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
361
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
362
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
363
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
364
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
365
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
366
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
367
+ "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
368
+ "shared.weight": "model-00001-of-00002.safetensors"
369
+ }
370
+ }