DrNicefellow commited on
Commit
be867be
1 Parent(s): 12d3e4d

Upload 13 files

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "clip_qkv": null,
8
+ "eos_token_id": 50279,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8192,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "olmo",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 1,
19
+ "pretraining_tp": 1,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.41.0",
25
+ "use_cache": true,
26
+ "vocab_size": 50304
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.41.0"
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb82139267271f12d73a6baca467888f9fed71cef031c6033803370bc1c5d52
3
+ size 16393633958
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7b3de15b2d84b9e76362c3affceea031cd1488383583f77580941b04699700
3
+ size 4967152029
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e77391ab8dd3cae41dfc7b419f5dd9800e65be9df8fef7f712089b860793c9
3
+ size 3229646818
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8196718592
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
79
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
86
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
87
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
88
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
92
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
100
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
102
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
104
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
105
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
106
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
108
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
111
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
113
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
114
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
116
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
117
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
118
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
119
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
120
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
121
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
122
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
123
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
124
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
132
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
140
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
147
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
148
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
149
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
150
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
152
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
192
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
201
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
202
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
204
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
206
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
210
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
212
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
228
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
229
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
232
+ }
233
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427e0ef134e24dc5d723850177ef0bf8dc594da43f9bcd18c8ed93c21ba73aa8
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|padding|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "|||IP_ADDRESS|||",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "|||EMAIL_ADDRESS|||",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
+ "content": "|||PHONE_NUMBER|||",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "50279": {
223
+ "content": "<|endoftext|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ }
230
+ },
231
+ "bos_token": null,
232
+ "clean_up_tokenization_spaces": true,
233
+ "eos_token": "<|endoftext|>",
234
+ "model_max_length": 1000000000000000019884624838656,
235
+ "pad_token": "<|padding|>",
236
+ "tokenizer_class": "GPTNeoXTokenizer",
237
+ "unk_token": null
238
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1fd3297bcb315b7c7d6b9f742905192ae81f2b10e332dd0ec9735cdbf68b8c1
3
+ size 5112