Hugging Face's logo

1995Austin
/
phifinetuning

Text Generation
Transformers
Safetensors
phi3
Generated from Trainer
trl
sft
conversational
custom_code
text-generation-inference
Model card Files
xet
 Community
1995Austin commited on
Commit
64798c7
·
verified ·
1 Parent(s): ce7abde

Upload Phi3ForCausalLM

Browse files
Files changed (8) hide show
  1. config.json +8 -8
  2. model-00001-of-00006.safetensors +3 -0
  3. model-00002-of-00006.safetensors +3 -0
  4. model-00003-of-00006.safetensors +3 -0
  5. model-00004-of-00006.safetensors +3 -0
  6. model-00005-of-00006.safetensors +3 -0
  7. model-00006-of-00006.safetensors +3 -0
  8. model.safetensors.index.json +244 -196
config.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
3
  "architectures": [
4
  "Phi3ForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
- "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
10
- "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
11
  },
12
  "bos_token_id": 1,
13
  "embd_pdrop": 0.0,
14
  "eos_token_id": 32000,
15
  "hidden_act": "silu",
16
- "hidden_size": 3072,
17
  "initializer_range": 0.02,
18
- "intermediate_size": 8192,
19
  "max_position_embeddings": 4096,
20
  "model_type": "phi3",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 32,
23
- "num_key_value_heads": 32,
24
  "original_max_position_embeddings": 4096,
25
  "pad_token_id": 32000,
26
  "resid_pdrop": 0.0,
 
1
  {
2
+ "_name_or_path": "microsoft/Phi-3-medium-4k-instruct",
3
  "architectures": [
4
  "Phi3ForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3-medium-4k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-medium-4k-instruct--modeling_phi3.Phi3ForCausalLM"
11
  },
12
  "bos_token_id": 1,
13
  "embd_pdrop": 0.0,
14
  "eos_token_id": 32000,
15
  "hidden_act": "silu",
16
+ "hidden_size": 5120,
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 17920,
19
  "max_position_embeddings": 4096,
20
  "model_type": "phi3",
21
+ "num_attention_heads": 40,
22
+ "num_hidden_layers": 40,
23
+ "num_key_value_heads": 10,
24
  "original_max_position_embeddings": 4096,
25
  "pad_token_id": 32000,
26
  "resid_pdrop": 0.0,
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cf194d1d79ff974c907c0c59654a3d0f83fbdeeaf1e294a5cb722fe8c8cfff
3
+ size 4915982920
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515df5b60aaecab88fb89a72e0c67f424144d4bb9a3985c2122137751ddfae6f
3
+ size 4954690720
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae48d629603e98d9b51bddae731ac33df1ab42fe6bf8cde195089e6f16ff1167
3
+ size 4902241352
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480fee507e9f0e0016d0fef178706429311e0b49c147b2d61a57ed1af31161d4
3
+ size 4771169120
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9332390c2fb602a6491541ccebd74ddd20638f338db7dc33ae6af0117ca961d2
3
+ size 4771169120
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1531950944588ab2e0d8de9f8a5037d0360cd75100fe69ca959169ab396bcc
3
+ size 3605251496
model.safetensors.index.json CHANGED
@@ -1,202 +1,250 @@
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": 27920476160
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.32.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.33.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.34.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
183
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
184
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
185
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
186
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.35.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
191
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
192
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
193
+ "model.layers.36.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
194
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
195
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
196
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
197
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
198
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.37.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
200
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
201
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.38.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.39.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
213
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
214
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
215
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
226
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
228
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
229
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
230
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
231
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
232
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
233
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
234
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
235
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
236
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
237
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
238
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
239
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
240
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
241
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
242
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
243
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
244
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
245
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
246
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
247
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
248
+ "model.norm.weight": "model-00006-of-00006.safetensors"
249
  }
250
  }