Hugging Face's logo

rahatneuron
/
llama3.1_8B_hellaswag_angular_7L

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
Community
rahatneuron commited on
Commit
cf1191a
·
verified ·
1 Parent(s): da88f46

Upload LlamaForCausalLM

Browse files
Files changed (8) hide show
  1. config.json +2 -2
  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 +229 -229
config.json CHANGED
@@ -28,8 +28,8 @@
28
  },
29
  "rope_theta": 500000.0,
30
  "tie_word_embeddings": false,
31
- "torch_dtype": "float16",
32
  "transformers_version": "4.51.3",
33
- "use_cache": true,
34
  "vocab_size": 128256
35
  }
 
28
  },
29
  "rope_theta": 500000.0,
30
  "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
  "transformers_version": "4.51.3",
33
+ "use_cache": false,
34
  "vocab_size": 128256
35
  }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2118d9a3a248a5342887c0dd63c630d8d6aad55c42f05c8e65dc338a00cd177e
3
+ size 4886466168
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3da02d0182089634249f1237d4a0e28922922d8d35864309e00db450c07e50
3
+ size 4832007448
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9055fa22a582fa182396ccfcaaf920af7c99f6542c66ce7d60fbd024ec2f66c
3
+ size 4999813112
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9f6b7e47b28721dcc308ef58c890f1773d0fdd7bfd0480ab70dce2d06918f6
3
+ size 4999813128
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca22eb7755f368e7107466099991272e68d9d10b84973c5c366e6716eb5382e0
3
+ size 4194489072
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6de87171d1da191c98104ebcbf2ee382501f3ca689b3577ac97bfa102d3d442
3
+ size 2101346432
model.safetensors.index.json CHANGED
@@ -1,235 +1,235 @@
1
  {
2
  "metadata": {
3
- "total_size": 13006954496
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
171
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
172
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
173
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
174
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
175
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
176
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
177
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
178
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
179
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
180
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
181
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
182
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
183
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
184
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
185
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
186
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
187
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
188
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
189
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
190
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
191
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
192
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
193
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
194
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
195
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
196
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
197
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
198
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
199
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
200
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
201
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
202
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
203
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
204
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
205
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
206
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
207
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
208
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
209
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
210
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
211
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
212
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
213
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
214
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
215
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
225
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
226
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
227
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
228
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
229
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
230
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
231
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
232
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
233
- "model.norm.weight": "model-00003-of-00003.safetensors"
234
  }
235
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 26013908992
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_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
171
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
172
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
173
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
174
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
175
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
176
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
177
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
178
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
179
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
180
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
181
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
182
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
183
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
184
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
185
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
186
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
187
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
188
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
189
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
190
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
191
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
192
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
193
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
194
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
195
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
196
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
197
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
198
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
199
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
200
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
201
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
202
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
203
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
204
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
205
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
206
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
207
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
208
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
209
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
210
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
211
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
212
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
213
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
214
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
215
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
216
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
217
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
218
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
219
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
220
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
221
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
222
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
223
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
224
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
225
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
226
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
227
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
228
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
229
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
230
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
231
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
232
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
233
+ "model.norm.weight": "model-00005-of-00006.safetensors"
234
  }
235
  }