XumengWen commited on
Commit
e7ca3dc
1 Parent(s): f6cd432

Delete LLaMA2_13b_GTL_diff

Browse files
LLaMA2_13b_GTL_diff/config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "_name_or_path": "/data/Blob_WestJP/shared/llama-2-hf/13B",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 1,
9
- "eos_token_id": 2,
10
- "hidden_act": "silu",
11
- "hidden_size": 5120,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 13824,
14
- "max_position_embeddings": 2048,
15
- "mlp_bias": false,
16
- "model_type": "llama",
17
- "num_attention_heads": 40,
18
- "num_hidden_layers": 40,
19
- "num_key_value_heads": 40,
20
- "pad_token_id": 0,
21
- "pretraining_tp": 1,
22
- "rms_norm_eps": 1e-05,
23
- "rope_scaling": null,
24
- "rope_theta": 10000.0,
25
- "tie_word_embeddings": false,
26
- "torch_dtype": "float32",
27
- "transformers_version": "4.41.1",
28
- "use_cache": true,
29
- "vocab_size": 32000
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
LLaMA2_13b_GTL_diff/generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.41.1"
7
- }
 
 
 
 
 
 
 
 
LLaMA2_13b_GTL_diff/model-00001-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbdb32f2339236162c38d8f929570971b4c391fa813d2130000f741644e7002c
3
- size 4881247856
 
 
 
 
LLaMA2_13b_GTL_diff/model-00002-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbd9587a122be162c1ba393d5869393e6f00fd4052d3d4da7c0eafe20508e468
3
- size 4970418112
 
 
 
 
LLaMA2_13b_GTL_diff/model-00003-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bd9175a5e219a0d9f06f10156fc2661d4bb1f2cb3b36c7a681ed26ada2e9106
3
- size 4970418120
 
 
 
 
LLaMA2_13b_GTL_diff/model-00004-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b60fba0381c97efd89e6b7ef732a13f4d3ba55f19b18de0c36cb114c3c387963
3
- size 4970418144
 
 
 
 
LLaMA2_13b_GTL_diff/model-00005-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6ef2af86831684ca1b86e26290a0681c7d3f13e85d99544c074caf2dcf740e0
3
- size 4970418144
 
 
 
 
LLaMA2_13b_GTL_diff/model-00006-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b82ff8f49844dfad503cd126c611975ecdca92a7801314832f326409b5d9131
3
- size 4792119040
 
 
 
 
LLaMA2_13b_GTL_diff/model-00007-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:075af1ff86d33c852a283e5ef4dee7dcb5719de723a4001481620f087f7564ae
3
- size 4792160232
 
 
 
 
LLaMA2_13b_GTL_diff/model-00008-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:125f1b26e8ab1dd5b6a211373c7459f186d9990dfea19689d8f1aaa043a4ac5b
3
- size 4792160224
 
 
 
 
LLaMA2_13b_GTL_diff/model-00009-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d785c502d7a2cbd440a0ab2adb315f9985a0f589bcd21b026c3a0bda59feda25
3
- size 4970418144
 
 
 
 
LLaMA2_13b_GTL_diff/model-00010-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:58ce334c09c90fe2669e6c61b8df59e2d84b77bc30bc2921322edf4719f2b4be
3
- size 4970418144
 
 
 
 
LLaMA2_13b_GTL_diff/model-00011-of-00011.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c1237af16f152523b6f1d10ac0f5f31196f8f6961de2a3697c7334d39d58db7
3
- size 2983303184
 
 
 
 
LLaMA2_13b_GTL_diff/model.safetensors.index.json DELETED
@@ -1,370 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 52063457280
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00011-of-00011.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
242
- "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
243
- "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
244
- "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
245
- "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
246
- "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
247
- "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
248
- "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
249
- "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
250
- "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
251
- "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
252
- "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
253
- "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
254
- "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
255
- "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
256
- "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
257
- "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
258
- "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
259
- "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
260
- "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
261
- "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
262
- "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
263
- "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
264
- "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
265
- "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
266
- "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
267
- "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
268
- "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
269
- "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
270
- "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
271
- "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
272
- "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
273
- "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
274
- "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
275
- "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
276
- "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
277
- "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
278
- "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
279
- "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
280
- "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
281
- "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
282
- "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
283
- "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
284
- "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
285
- "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
286
- "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
287
- "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
288
- "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
289
- "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
290
- "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
291
- "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
292
- "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
293
- "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
294
- "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
295
- "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
296
- "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
297
- "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
298
- "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
299
- "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
300
- "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
301
- "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
302
- "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
303
- "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
304
- "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
305
- "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
306
- "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
307
- "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
308
- "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
309
- "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
310
- "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
311
- "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
312
- "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
313
- "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
314
- "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
315
- "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
316
- "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
317
- "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
318
- "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
319
- "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
320
- "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
321
- "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
322
- "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
323
- "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
324
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
325
- "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
326
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
327
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
328
- "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
329
- "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
330
- "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
331
- "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
332
- "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
333
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
334
- "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
335
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
336
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
337
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
338
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
339
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
340
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
341
- "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
342
- "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
343
- "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
344
- "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
345
- "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
346
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
347
- "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
348
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
349
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
350
- "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
351
- "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
352
- "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
353
- "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
354
- "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
355
- "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
356
- "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
357
- "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
358
- "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
359
- "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
360
- "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
361
- "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
362
- "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
363
- "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
364
- "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
365
- "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
366
- "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
367
- "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
368
- "model.norm.weight": "model-00011-of-00011.safetensors"
369
- }
370
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
LLaMA2_13b_GTL_diff/special_tokens_map.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
LLaMA2_13b_GTL_diff/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
LLaMA2_13b_GTL_diff/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
LLaMA2_13b_GTL_diff/tokenizer_config.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
- },
30
- "bos_token": "<s>",
31
- "clean_up_tokenization_spaces": false,
32
- "eos_token": "</s>",
33
- "legacy": true,
34
- "model_max_length": 1000000000000000019884624838656,
35
- "pad_token": null,
36
- "sp_model_kwargs": {},
37
- "tokenizer_class": "LlamaTokenizer",
38
- "unk_token": "<unk>",
39
- "use_default_system_prompt": false
40
- }