shreyaspimpalgaonkar commited on
Commit
b2a6f1d
1 Parent(s): f1733f0

Upload model

Browse files
config.json CHANGED
@@ -1,12 +1,13 @@
1
  {
2
- "_name_or_path": "sciphi/triplex",
3
  "architectures": [
4
- "Phi3ForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "auto_map": {
8
- "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
9
- "AutoModel": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
10
  "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
11
  },
12
  "bos_token_id": 1,
@@ -126,14 +127,13 @@
126
  2.8999999999999977,
127
  3.049999999999997
128
  ],
129
- "type": "longrope"
130
  },
131
  "rope_theta": 10000.0,
132
  "sliding_window": 262144,
133
  "tie_word_embeddings": false,
134
  "torch_dtype": "bfloat16",
135
- "transformers_version": "4.40.2",
136
- "use_cache": true,
137
- "attention_bias": false,
138
  "vocab_size": 32064
139
- }
 
1
  {
2
+ "_name_or_path": ".",
3
  "architectures": [
4
+ "Phi3Model"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModel": "modeling_phi3.Phi3ForCausalLM",
11
  "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
12
  },
13
  "bos_token_id": 1,
 
127
  2.8999999999999977,
128
  3.049999999999997
129
  ],
130
+ "type": "longrope"
131
  },
132
  "rope_theta": 10000.0,
133
  "sliding_window": 262144,
134
  "tie_word_embeddings": false,
135
  "torch_dtype": "bfloat16",
136
+ "transformers_version": "4.43.0.dev0",
137
+ "use_cache": false,
 
138
  "vocab_size": 32064
139
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243b23e2ba84c6088a77298451025e875e45a89118c26ff2a14644208cd338cb
3
- size 4972489328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8865d8422db7890a08f673e497648ae30eb4a514a4aef14fd626c6ea64fa77c
3
+ size 4972488560
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3921621dd4d3a28b5509596d4dfd51f72db53b1c478056e512df2114d655de7a
3
- size 2669692552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef254871d9788bb14faac6e77253f76220c7714063fe8bcbf00c273e6253cb64
3
+ size 2472690824
model.safetensors.index.json CHANGED
@@ -1,202 +1,201 @@
1
  {
2
  "metadata": {
3
- "total_size": 7642159104
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00002-of-00002.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
93
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
94
- "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
95
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
98
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
- "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
101
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
103
- "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
104
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
105
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
106
- "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
107
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
- "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
110
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
111
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
112
- "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
113
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
114
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
- "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
116
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
117
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
118
- "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
119
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
- "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
122
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
123
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
124
- "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
125
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
126
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
- "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
128
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
129
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
130
- "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
131
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
- "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
134
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
- "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
137
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
139
- "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
140
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
- "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
143
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
145
- "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
146
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
- "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
155
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
157
- "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
158
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
160
- "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
161
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
162
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
- "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
167
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
170
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
- "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
- "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
176
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
- "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
179
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
- "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
182
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
184
- "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
185
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
- "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
188
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
- "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
191
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
194
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
- "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
199
- "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
200
- "model.norm.weight": "model-00002-of-00002.safetensors"
201
  }
202
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 7445157888
4
  },
5
  "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
10
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
12
+ "layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
13
+ "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
15
+ "layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
19
+ "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
25
+ "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
28
+ "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
31
+ "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
37
+ "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
43
+ "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
49
+ "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
54
+ "layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
55
+ "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
61
+ "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
67
+ "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
70
+ "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
73
+ "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
76
+ "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
77
+ "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
79
+ "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
85
+ "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
88
+ "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
90
+ "layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
91
+ "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
93
+ "layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
97
+ "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
100
+ "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
102
+ "layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
103
+ "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
105
+ "layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
106
+ "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
108
+ "layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
109
+ "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
110
+ "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
111
+ "layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
115
+ "layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
117
+ "layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
118
+ "layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
120
+ "layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
121
+ "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
122
+ "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
123
+ "layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
124
+ "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
127
+ "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
+ "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
129
+ "layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
132
+ "layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
133
+ "layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
136
+ "layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
137
+ "layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
139
+ "layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
144
+ "layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
145
+ "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
151
+ "layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
156
+ "layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
157
+ "layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
159
+ "layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
160
+ "layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
162
+ "layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
163
+ "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
169
+ "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
175
+ "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
178
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
180
+ "layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
181
+ "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
183
+ "layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
187
+ "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
190
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
192
+ "layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
193
+ "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
196
+ "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
198
+ "layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
199
+ "norm.weight": "model-00002-of-00002.safetensors"
 
200
  }
201
  }