Shawn Tan commited on
Commit
8c1b2ba
·
1 Parent(s): c2541c6

New model files with new dolomite-engine.

Browse files
config.json CHANGED
@@ -15,7 +15,7 @@
15
  "m_emb": 12,
16
  "m_residual": 0.22,
17
  "m_width": 9,
18
- "model_type": "sb_dolomite",
19
  "multi_query": false,
20
  "n_embd": 2304,
21
  "n_head": 36,
@@ -25,10 +25,8 @@
25
  "normalization_function": "rmsnorm",
26
  "num_key_value_heads": 36,
27
  "pad_token_id": 50256,
28
- "position_embedding_type": "rope",
29
  "resid_pdrop": 0,
30
- "rope_scaling": null,
31
- "rope_theta": 10000,
32
  "sb_remainder": false,
33
  "scale_attn_weights": true,
34
  "transformers_version": "4.45.0",
 
15
  "m_emb": 12,
16
  "m_residual": 0.22,
17
  "m_width": 9,
18
+ "model_type": "stickbreaking",
19
  "multi_query": false,
20
  "n_embd": 2304,
21
  "n_head": 36,
 
25
  "normalization_function": "rmsnorm",
26
  "num_key_value_heads": 36,
27
  "pad_token_id": 50256,
28
+ "position_embedding_type": "nope",
29
  "resid_pdrop": 0,
 
 
30
  "sb_remainder": false,
31
  "scale_attn_weights": true,
32
  "transformers_version": "4.45.0",
model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79121698b2886a5af8a54e2a5bb6c5787d2825c99ae77b641c49988348217ea6
3
- size 4956581312
 
 
 
 
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:744ec7657e286b2b197e0fa70a00c0c2ad16416fa08c5e8e4a39f2a3e1c67cf9
3
- size 2070391576
 
 
 
 
model.safetensors.index.json CHANGED
@@ -1,249 +1,249 @@
1
  {
2
  "metadata": {
3
- "total_size": 7026946560
4
  },
5
  "weight_map": {
6
- "transformer.wte.weight": "model-00001-of-00002.safetensors",
7
- "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
8
- "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
9
- "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
10
- "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
11
- "transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
12
- "transformer.h.24.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
13
- "transformer.h.32.attn.c_proj.weight": "model-00001-of-00002.safetensors",
14
- "transformer.h.34.ln_1.weight": "model-00001-of-00002.safetensors",
15
- "transformer.h.34.ln_2.weight": "model-00001-of-00002.safetensors",
16
- "transformer.h.34.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
17
- "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
18
- "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
19
- "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
20
- "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
21
- "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
22
- "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
23
- "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
24
- "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
25
- "transformer.h.36.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
26
- "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
27
- "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
28
- "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
29
- "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
30
- "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
31
- "transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
32
- "transformer.h.26.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
33
- "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
34
- "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
35
- "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
36
- "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
37
- "transformer.h.37.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
38
- "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
39
- "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
40
- "transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
41
- "transformer.h.26.attn.c_attn.weight": "model-00001-of-00002.safetensors",
42
- "transformer.h.32.ln_1.weight": "model-00001-of-00002.safetensors",
43
- "transformer.h.32.ln_2.weight": "model-00001-of-00002.safetensors",
44
- "transformer.h.32.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
45
- "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
46
- "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
47
- "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
48
- "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
49
- "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
50
- "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
51
- "transformer.h.29.attn.c_proj.weight": "model-00001-of-00002.safetensors",
52
- "transformer.h.31.ln_1.weight": "model-00001-of-00002.safetensors",
53
- "transformer.h.31.ln_2.weight": "model-00001-of-00002.safetensors",
54
- "transformer.h.31.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
55
- "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
56
- "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
57
- "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
58
- "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
59
- "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
60
- "transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
61
- "transformer.h.27.attn.c_attn.weight": "model-00001-of-00002.safetensors",
62
- "transformer.h.33.ln_1.weight": "model-00001-of-00002.safetensors",
63
- "transformer.h.33.attn.c_proj.weight": "model-00001-of-00002.safetensors",
64
- "transformer.h.35.ln_1.weight": "model-00001-of-00002.safetensors",
65
- "transformer.h.35.attn.c_proj.weight": "model-00001-of-00002.safetensors",
66
- "transformer.h.37.ln_2.weight": "model-00001-of-00002.safetensors",
67
- "transformer.h.37.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
68
- "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
69
- "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
70
- "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
71
- "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
72
- "transformer.h.28.attn.c_attn.weight": "model-00001-of-00002.safetensors",
73
- "transformer.h.33.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
74
- "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
75
- "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
76
- "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
77
- "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
78
- "transformer.h.30.attn.c_proj.weight": "model-00001-of-00002.safetensors",
79
- "transformer.h.32.attn.c_attn.weight": "model-00001-of-00002.safetensors",
80
- "transformer.h.38.ln_1.weight": "model-00001-of-00002.safetensors",
81
- "transformer.h.38.attn.c_attn.weight": "model-00001-of-00002.safetensors",
82
- "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
83
- "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
84
- "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
85
- "transformer.h.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
86
- "transformer.h.30.ln_2.weight": "model-00001-of-00002.safetensors",
87
- "transformer.h.30.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
88
- "transformer.h.38.attn.c_proj.weight": "model-00001-of-00002.safetensors",
89
- "transformer.ln_f.weight": "model-00001-of-00002.safetensors",
90
- "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
91
- "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
92
- "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
93
- "transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
94
- "transformer.h.23.attn.c_proj.weight": "model-00001-of-00002.safetensors",
95
- "transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
96
- "transformer.h.25.attn.c_attn.weight": "model-00001-of-00002.safetensors",
97
- "transformer.h.31.attn.c_attn.weight": "model-00001-of-00002.safetensors",
98
- "transformer.h.36.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
99
- "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
100
- "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
101
- "transformer.h.27.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
102
- "transformer.h.35.ln_2.weight": "model-00001-of-00002.safetensors",
103
- "transformer.h.35.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
104
- "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
105
- "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
106
- "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
107
- "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
108
- "transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
109
- "transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
110
- "transformer.h.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
111
- "transformer.h.31.attn.c_proj.weight": "model-00001-of-00002.safetensors",
112
- "transformer.h.32.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
113
- "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
114
- "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
115
- "transformer.h.25.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
116
- "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
117
- "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
118
- "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
119
- "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
120
- "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
121
- "transformer.h.36.ln_1.weight": "model-00001-of-00002.safetensors",
122
- "transformer.h.36.attn.c_proj.weight": "model-00001-of-00002.safetensors",
123
- "transformer.h.38.ln_2.weight": "model-00001-of-00002.safetensors",
124
- "transformer.h.38.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
125
- "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
126
- "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
127
- "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
128
- "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
129
- "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
130
- "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
131
- "transformer.h.34.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
132
- "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
133
- "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
134
- "transformer.h.35.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
135
- "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
136
- "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
137
- "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
138
- "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
139
- "transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
140
- "transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
141
- "transformer.h.29.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
142
- "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
143
- "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
144
- "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
145
- "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
146
- "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
147
- "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
148
- "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
149
- "transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
150
- "transformer.h.27.attn.c_proj.weight": "model-00001-of-00002.safetensors",
151
- "transformer.h.29.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
152
- "transformer.h.37.attn.c_attn.weight": "model-00001-of-00002.safetensors",
153
- "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
154
- "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
155
- "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
156
- "transformer.h.25.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
157
- "transformer.h.33.ln_2.weight": "model-00001-of-00002.safetensors",
158
- "transformer.h.33.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
159
- "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
160
- "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
161
- "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
- "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
163
- "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
164
- "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
165
- "transformer.h.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
166
- "transformer.h.38.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
167
- "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
168
- "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
169
- "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
170
- "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
171
- "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
172
- "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
173
- "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
174
- "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
175
- "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
176
- "transformer.h.33.attn.c_attn.weight": "model-00002-of-00002.safetensors",
177
- "transformer.h.39.ln_1.weight": "model-00002-of-00002.safetensors",
178
- "transformer.h.39.attn.c_proj.weight": "model-00002-of-00002.safetensors",
179
- "transformer.h.3.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
180
- "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
181
- "transformer.h.28.ln_1.weight": "model-00002-of-00002.safetensors",
182
- "transformer.h.28.attn.c_proj.weight": "model-00002-of-00002.safetensors",
183
- "transformer.h.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
184
- "transformer.h.3.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
185
- "transformer.h.13.attn.c_attn.weight": "model-00002-of-00002.safetensors",
186
- "transformer.h.18.ln_1.weight": "model-00002-of-00002.safetensors",
187
- "transformer.h.18.attn.c_attn.weight": "model-00002-of-00002.safetensors",
188
- "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
189
- "transformer.h.39.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
190
- "transformer.h.4.ln_1.weight": "model-00002-of-00002.safetensors",
191
- "transformer.h.6.ln_2.weight": "model-00002-of-00002.safetensors",
192
- "transformer.h.7.attn.c_proj.weight": "model-00002-of-00002.safetensors",
193
- "transformer.h.9.ln_2.weight": "model-00002-of-00002.safetensors",
194
- "transformer.h.9.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
195
- "transformer.h.24.ln_1.weight": "model-00002-of-00002.safetensors",
196
- "transformer.h.24.attn.c_attn.weight": "model-00002-of-00002.safetensors",
197
- "transformer.h.30.ln_1.weight": "model-00002-of-00002.safetensors",
198
- "transformer.h.30.attn.c_attn.weight": "model-00002-of-00002.safetensors",
199
- "transformer.h.35.attn.c_attn.weight": "model-00002-of-00002.safetensors",
200
- "transformer.h.4.attn.c_attn.weight": "model-00002-of-00002.safetensors",
201
- "transformer.h.11.ln_1.weight": "model-00002-of-00002.safetensors",
202
- "transformer.h.11.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
203
- "transformer.h.26.attn.c_proj.weight": "model-00002-of-00002.safetensors",
204
- "transformer.h.28.ln_2.weight": "model-00002-of-00002.safetensors",
205
- "transformer.h.29.attn.c_attn.weight": "model-00002-of-00002.safetensors",
206
- "transformer.h.34.attn.c_attn.weight": "model-00002-of-00002.safetensors",
207
- "transformer.h.4.attn.c_proj.weight": "model-00002-of-00002.safetensors",
208
- "transformer.h.8.ln_2.weight": "model-00002-of-00002.safetensors",
209
- "transformer.h.9.attn.c_attn.weight": "model-00002-of-00002.safetensors",
210
- "transformer.h.14.attn.c_attn.weight": "model-00002-of-00002.safetensors",
211
- "transformer.h.18.attn.c_proj.weight": "model-00002-of-00002.safetensors",
212
- "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
213
- "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
214
- "transformer.h.4.ln_2.weight": "model-00002-of-00002.safetensors",
215
- "transformer.h.6.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
216
- "transformer.h.21.ln_1.weight": "model-00002-of-00002.safetensors",
217
- "transformer.h.21.ln_2.weight": "model-00002-of-00002.safetensors",
218
- "transformer.h.22.ln_1.weight": "model-00002-of-00002.safetensors",
219
- "transformer.h.22.attn.c_proj.weight": "model-00002-of-00002.safetensors",
220
- "transformer.h.24.attn.c_proj.weight": "model-00002-of-00002.safetensors",
221
- "transformer.h.25.attn.c_proj.weight": "model-00002-of-00002.safetensors",
222
- "transformer.h.27.ln_2.weight": "model-00002-of-00002.safetensors",
223
- "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
224
- "transformer.h.4.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
225
- "transformer.h.20.ln_1.weight": "model-00002-of-00002.safetensors",
226
- "transformer.h.21.attn.c_attn.weight": "model-00002-of-00002.safetensors",
227
- "transformer.h.26.ln_2.weight": "model-00002-of-00002.safetensors",
228
- "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
229
- "transformer.h.34.attn.c_proj.weight": "model-00002-of-00002.safetensors",
230
- "transformer.h.36.ln_2.weight": "model-00002-of-00002.safetensors",
231
- "transformer.h.37.ln_1.weight": "model-00002-of-00002.safetensors",
232
- "transformer.h.37.attn.c_proj.weight": "model-00002-of-00002.safetensors",
233
- "transformer.h.39.attn.c_attn.weight": "model-00002-of-00002.safetensors",
234
- "transformer.h.4.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
235
- "transformer.h.13.attn.c_proj.weight": "model-00002-of-00002.safetensors",
236
- "transformer.h.15.attn.c_proj.weight": "model-00002-of-00002.safetensors",
237
- "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
238
- "transformer.h.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
239
- "transformer.h.39.ln_2.weight": "model-00002-of-00002.safetensors",
240
- "transformer.h.39.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
241
- "transformer.h.5.ln_1.weight": "model-00002-of-00002.safetensors",
242
- "transformer.h.6.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
243
- "transformer.h.14.attn.c_proj.weight": "model-00002-of-00002.safetensors",
244
- "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
245
- "transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
246
- "transformer.h.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
247
- "transformer.h.36.attn.c_attn.weight": "model-00002-of-00002.safetensors"
248
  }
249
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 14053893120
4
  },
5
  "weight_map": {
6
+ "transformer.wte.weight": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.24.ln_2.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.24.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.h.32.attn.c_proj.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.h.34.ln_1.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.34.ln_2.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.34.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.15.ln_1.weight": "model-00001-of-00003.safetensors",
21
+ "transformer.h.15.ln_2.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.16.ln_1.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.16.attn.c_attn.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
25
+ "transformer.h.36.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
27
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.15.attn.c_attn.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.h.19.ln_1.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.20.attn.c_attn.weight": "model-00001-of-00003.safetensors",
31
+ "transformer.h.26.ln_1.weight": "model-00001-of-00003.safetensors",
32
+ "transformer.h.26.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
33
+ "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
34
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
35
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.h.37.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
38
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
39
+ "transformer.h.19.attn.c_attn.weight": "model-00001-of-00003.safetensors",
40
+ "transformer.h.25.ln_2.weight": "model-00001-of-00003.safetensors",
41
+ "transformer.h.26.attn.c_attn.weight": "model-00001-of-00003.safetensors",
42
+ "transformer.h.32.ln_1.weight": "model-00001-of-00003.safetensors",
43
+ "transformer.h.32.ln_2.weight": "model-00001-of-00003.safetensors",
44
+ "transformer.h.32.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
45
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
47
+ "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
48
+ "transformer.h.14.ln_2.weight": "model-00001-of-00003.safetensors",
49
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
50
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
51
+ "transformer.h.29.attn.c_proj.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.h.31.ln_1.weight": "model-00001-of-00003.safetensors",
53
+ "transformer.h.31.ln_2.weight": "model-00001-of-00003.safetensors",
54
+ "transformer.h.31.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
55
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
56
+ "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
57
+ "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
58
+ "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
59
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
60
+ "transformer.h.22.attn.c_attn.weight": "model-00001-of-00003.safetensors",
61
+ "transformer.h.27.attn.c_attn.weight": "model-00001-of-00003.safetensors",
62
+ "transformer.h.33.ln_1.weight": "model-00001-of-00003.safetensors",
63
+ "transformer.h.33.attn.c_proj.weight": "model-00001-of-00003.safetensors",
64
+ "transformer.h.35.ln_1.weight": "model-00001-of-00003.safetensors",
65
+ "transformer.h.35.attn.c_proj.weight": "model-00001-of-00003.safetensors",
66
+ "transformer.h.37.ln_2.weight": "model-00001-of-00003.safetensors",
67
+ "transformer.h.37.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
68
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
69
+ "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
70
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors",
71
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
72
+ "transformer.h.28.attn.c_attn.weight": "model-00001-of-00003.safetensors",
73
+ "transformer.h.33.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
74
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
75
+ "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
76
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
77
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
78
+ "transformer.h.30.attn.c_proj.weight": "model-00001-of-00003.safetensors",
79
+ "transformer.h.32.attn.c_attn.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.h.38.ln_1.weight": "model-00001-of-00003.safetensors",
81
+ "transformer.h.38.attn.c_attn.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
83
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.h.20.attn.c_proj.weight": "model-00001-of-00003.safetensors",
85
+ "transformer.h.22.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
86
+ "transformer.h.30.ln_2.weight": "model-00001-of-00003.safetensors",
87
+ "transformer.h.30.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
88
+ "transformer.h.38.attn.c_proj.weight": "model-00001-of-00003.safetensors",
89
+ "transformer.ln_f.weight": "model-00001-of-00003.safetensors",
90
+ "transformer.h.1.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
91
+ "transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.h.25.attn.c_attn.weight": "model-00002-of-00003.safetensors",
97
+ "transformer.h.31.attn.c_attn.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.36.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
99
+ "transformer.h.1.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.35.ln_2.weight": "model-00002-of-00003.safetensors",
103
+ "transformer.h.35.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors",
105
+ "transformer.h.5.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
107
+ "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
109
+ "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
111
+ "transformer.h.31.attn.c_proj.weight": "model-00002-of-00003.safetensors",
112
+ "transformer.h.32.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
113
+ "transformer.h.2.attn.c_attn.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.10.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
115
+ "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
116
+ "transformer.h.2.attn.c_proj.weight": "model-00002-of-00003.safetensors",
117
+ "transformer.h.8.attn.c_attn.weight": "model-00002-of-00003.safetensors",
118
+ "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
119
+ "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
120
+ "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
121
+ "transformer.h.36.ln_1.weight": "model-00002-of-00003.safetensors",
122
+ "transformer.h.36.attn.c_proj.weight": "model-00002-of-00003.safetensors",
123
+ "transformer.h.38.ln_2.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.38.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
125
+ "transformer.h.2.ln_2.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.6.ln_1.weight": "model-00002-of-00003.safetensors",
127
+ "transformer.h.7.attn.c_attn.weight": "model-00002-of-00003.safetensors",
128
+ "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
129
+ "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
130
+ "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
131
+ "transformer.h.34.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
132
+ "transformer.h.2.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
133
+ "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
134
+ "transformer.h.35.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
135
+ "transformer.h.2.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
136
+ "transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
137
+ "transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
138
+ "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
139
+ "transformer.h.29.ln_1.weight": "model-00002-of-00003.safetensors",
140
+ "transformer.h.29.ln_2.weight": "model-00002-of-00003.safetensors",
141
+ "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
142
+ "transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors",
143
+ "transformer.h.6.attn.c_attn.weight": "model-00002-of-00003.safetensors",
144
+ "transformer.h.11.ln_2.weight": "model-00002-of-00003.safetensors",
145
+ "transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
146
+ "transformer.h.12.attn.c_attn.weight": "model-00002-of-00003.safetensors",
147
+ "transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
148
+ "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
149
+ "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
150
+ "transformer.h.27.attn.c_proj.weight": "model-00002-of-00003.safetensors",
151
+ "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
152
+ "transformer.h.37.attn.c_attn.weight": "model-00002-of-00003.safetensors",
153
+ "transformer.h.3.attn.c_attn.weight": "model-00002-of-00003.safetensors",
154
+ "transformer.h.10.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
155
+ "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
156
+ "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
157
+ "transformer.h.33.ln_2.weight": "model-00002-of-00003.safetensors",
158
+ "transformer.h.33.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
159
+ "transformer.h.3.attn.c_proj.weight": "model-00002-of-00003.safetensors",
160
+ "transformer.h.8.attn.c_proj.weight": "model-00002-of-00003.safetensors",
161
+ "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
162
+ "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
163
+ "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
164
+ "transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
165
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
166
+ "transformer.h.38.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
167
+ "transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors",
168
+ "transformer.h.6.attn.c_proj.weight": "model-00002-of-00003.safetensors",
169
+ "transformer.h.9.ln_1.weight": "model-00002-of-00003.safetensors",
170
+ "transformer.h.9.attn.c_proj.weight": "model-00002-of-00003.safetensors",
171
+ "transformer.h.10.ln_1.weight": "model-00002-of-00003.safetensors",
172
+ "transformer.h.10.attn.c_attn.weight": "model-00002-of-00003.safetensors",
173
+ "transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
174
+ "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
175
+ "transformer.h.17.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
176
+ "transformer.h.33.attn.c_attn.weight": "model-00003-of-00003.safetensors",
177
+ "transformer.h.39.ln_1.weight": "model-00003-of-00003.safetensors",
178
+ "transformer.h.39.attn.c_proj.weight": "model-00003-of-00003.safetensors",
179
+ "transformer.h.3.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
180
+ "transformer.h.19.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
181
+ "transformer.h.28.ln_1.weight": "model-00003-of-00003.safetensors",
182
+ "transformer.h.28.attn.c_proj.weight": "model-00003-of-00003.safetensors",
183
+ "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
184
+ "transformer.h.3.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
185
+ "transformer.h.13.attn.c_attn.weight": "model-00003-of-00003.safetensors",
186
+ "transformer.h.18.ln_1.weight": "model-00003-of-00003.safetensors",
187
+ "transformer.h.18.attn.c_attn.weight": "model-00003-of-00003.safetensors",
188
+ "transformer.h.24.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
189
+ "transformer.h.39.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
190
+ "transformer.h.4.ln_1.weight": "model-00003-of-00003.safetensors",
191
+ "transformer.h.6.ln_2.weight": "model-00003-of-00003.safetensors",
192
+ "transformer.h.7.attn.c_proj.weight": "model-00003-of-00003.safetensors",
193
+ "transformer.h.9.ln_2.weight": "model-00003-of-00003.safetensors",
194
+ "transformer.h.9.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
195
+ "transformer.h.24.ln_1.weight": "model-00003-of-00003.safetensors",
196
+ "transformer.h.24.attn.c_attn.weight": "model-00003-of-00003.safetensors",
197
+ "transformer.h.30.ln_1.weight": "model-00003-of-00003.safetensors",
198
+ "transformer.h.30.attn.c_attn.weight": "model-00003-of-00003.safetensors",
199
+ "transformer.h.35.attn.c_attn.weight": "model-00003-of-00003.safetensors",
200
+ "transformer.h.4.attn.c_attn.weight": "model-00003-of-00003.safetensors",
201
+ "transformer.h.11.ln_1.weight": "model-00003-of-00003.safetensors",
202
+ "transformer.h.11.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
203
+ "transformer.h.26.attn.c_proj.weight": "model-00003-of-00003.safetensors",
204
+ "transformer.h.28.ln_2.weight": "model-00003-of-00003.safetensors",
205
+ "transformer.h.29.attn.c_attn.weight": "model-00003-of-00003.safetensors",
206
+ "transformer.h.34.attn.c_attn.weight": "model-00003-of-00003.safetensors",
207
+ "transformer.h.4.attn.c_proj.weight": "model-00003-of-00003.safetensors",
208
+ "transformer.h.8.ln_2.weight": "model-00003-of-00003.safetensors",
209
+ "transformer.h.9.attn.c_attn.weight": "model-00003-of-00003.safetensors",
210
+ "transformer.h.14.attn.c_attn.weight": "model-00003-of-00003.safetensors",
211
+ "transformer.h.18.attn.c_proj.weight": "model-00003-of-00003.safetensors",
212
+ "transformer.h.20.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
213
+ "transformer.h.28.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
214
+ "transformer.h.4.ln_2.weight": "model-00003-of-00003.safetensors",
215
+ "transformer.h.6.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
216
+ "transformer.h.21.ln_1.weight": "model-00003-of-00003.safetensors",
217
+ "transformer.h.21.ln_2.weight": "model-00003-of-00003.safetensors",
218
+ "transformer.h.22.ln_1.weight": "model-00003-of-00003.safetensors",
219
+ "transformer.h.22.attn.c_proj.weight": "model-00003-of-00003.safetensors",
220
+ "transformer.h.24.attn.c_proj.weight": "model-00003-of-00003.safetensors",
221
+ "transformer.h.25.attn.c_proj.weight": "model-00003-of-00003.safetensors",
222
+ "transformer.h.27.ln_2.weight": "model-00003-of-00003.safetensors",
223
+ "transformer.h.27.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
224
+ "transformer.h.4.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
225
+ "transformer.h.20.ln_1.weight": "model-00003-of-00003.safetensors",
226
+ "transformer.h.21.attn.c_attn.weight": "model-00003-of-00003.safetensors",
227
+ "transformer.h.26.ln_2.weight": "model-00003-of-00003.safetensors",
228
+ "transformer.h.26.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
229
+ "transformer.h.34.attn.c_proj.weight": "model-00003-of-00003.safetensors",
230
+ "transformer.h.36.ln_2.weight": "model-00003-of-00003.safetensors",
231
+ "transformer.h.37.ln_1.weight": "model-00003-of-00003.safetensors",
232
+ "transformer.h.37.attn.c_proj.weight": "model-00003-of-00003.safetensors",
233
+ "transformer.h.39.attn.c_attn.weight": "model-00003-of-00003.safetensors",
234
+ "transformer.h.4.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
235
+ "transformer.h.13.attn.c_proj.weight": "model-00003-of-00003.safetensors",
236
+ "transformer.h.15.attn.c_proj.weight": "model-00003-of-00003.safetensors",
237
+ "transformer.h.16.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
238
+ "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
239
+ "transformer.h.39.ln_2.weight": "model-00003-of-00003.safetensors",
240
+ "transformer.h.39.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
241
+ "transformer.h.5.ln_1.weight": "model-00003-of-00003.safetensors",
242
+ "transformer.h.6.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
243
+ "transformer.h.14.attn.c_proj.weight": "model-00003-of-00003.safetensors",
244
+ "transformer.h.15.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
245
+ "transformer.h.23.attn.c_attn.weight": "model-00003-of-00003.safetensors",
246
+ "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
247
+ "transformer.h.36.attn.c_attn.weight": "model-00003-of-00003.safetensors"
248
  }
249
  }
special_tokens_map.json CHANGED
File without changes
tokenizer.json CHANGED
File without changes
tokenizer_config.json CHANGED
File without changes