mzbac commited on
Commit
fa4cf3e
1 Parent(s): 7a5b54e

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,28 +1,27 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
- "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 500000.0,
23
- "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
- "transformers_version": "4.40.0",
26
- "use_cache": true,
27
- "vocab_size": 128256
28
- }
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 500000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.40.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 128256
27
+ }
 
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f28307a4b8813e67b17ad2b17d03e732ec27cd61601dd6d2a4b80ea79dffb29d
3
- size 4976698592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343be4a4d457190cf99cc58db888981439a365b5cb532e0234c3d4e6f215644a
3
+ size 5295466428
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af5528998d195d3bbde98990be437080df9df70c87466d4b7c97ab01ec36db8a
3
- size 4999802616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ec8297ae6bc951922d278f6038bafe1b3f60812b8f370d21ac09a9698052c7
3
+ size 5352157832
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efa8fdc5dcc8a997e08f89d56d060deeb0e5457daaa872638c3b80f7c823f414
3
- size 4915916080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff05fa245372d569061d0e4eb59559b726c5c730abe86c73255d84877374bfa
3
+ size 4362258775
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acf8a53f67ac4c8b48eac12ae723148ff3e2dd3322340fc52c55dc514bc4c361
3
- size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638452373abba2c197f5d86fae5d836e844e2aeffac0ec275b9f6b1162d524a0
3
+ size 1050673279
model.safetensors.index.json CHANGED
@@ -1,298 +1,298 @@
1
  {
2
- "metadata": {
3
- "total_size": 16060522496
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00004-of-00004.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.norm.weight": "model-00004-of-00004.safetensors"
297
- }
298
- }
 
1
  {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.norm.weight": "model-00003-of-00004.safetensors"
297
+ }
298
+ }
tokenizer.json CHANGED
@@ -2329,10 +2329,69 @@
2329
  ]
2330
  },
2331
  "post_processor": {
2332
- "type": "ByteLevel",
2333
- "add_prefix_space": true,
2334
- "trim_offsets": false,
2335
- "use_regex": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2336
  },
2337
  "decoder": {
2338
  "type": "ByteLevel",
 
2329
  ]
2330
  },
2331
  "post_processor": {
2332
+ "type": "Sequence",
2333
+ "processors": [
2334
+ {
2335
+ "type": "ByteLevel",
2336
+ "add_prefix_space": true,
2337
+ "trim_offsets": false,
2338
+ "use_regex": true
2339
+ },
2340
+ {
2341
+ "type": "TemplateProcessing",
2342
+ "single": [
2343
+ {
2344
+ "SpecialToken": {
2345
+ "id": "<|begin_of_text|>",
2346
+ "type_id": 0
2347
+ }
2348
+ },
2349
+ {
2350
+ "Sequence": {
2351
+ "id": "A",
2352
+ "type_id": 0
2353
+ }
2354
+ }
2355
+ ],
2356
+ "pair": [
2357
+ {
2358
+ "SpecialToken": {
2359
+ "id": "<|begin_of_text|>",
2360
+ "type_id": 0
2361
+ }
2362
+ },
2363
+ {
2364
+ "Sequence": {
2365
+ "id": "A",
2366
+ "type_id": 0
2367
+ }
2368
+ },
2369
+ {
2370
+ "SpecialToken": {
2371
+ "id": "<|begin_of_text|>",
2372
+ "type_id": 1
2373
+ }
2374
+ },
2375
+ {
2376
+ "Sequence": {
2377
+ "id": "B",
2378
+ "type_id": 1
2379
+ }
2380
+ }
2381
+ ],
2382
+ "special_tokens": {
2383
+ "<|begin_of_text|>": {
2384
+ "id": "<|begin_of_text|>",
2385
+ "ids": [
2386
+ 128000
2387
+ ],
2388
+ "tokens": [
2389
+ "<|begin_of_text|>"
2390
+ ]
2391
+ }
2392
+ }
2393
+ }
2394
+ ]
2395
  },
2396
  "decoder": {
2397
  "type": "ByteLevel",
tokenizer_config.json CHANGED
@@ -2050,7 +2050,7 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|end_of_text|>",
2056
  "model_input_names": [
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|end_of_text|>",
2056
  "model_input_names": [