typeof commited on
Commit
7b64c30
1 Parent(s): 3929aad
config.json CHANGED
@@ -1,24 +1,25 @@
1
  {
 
2
  "architectures": [
3
  "MistralForCausalLM"
4
  ],
5
  "bos_token_id": 1,
6
  "eos_token_id": 2,
7
  "hidden_act": "silu",
8
- "hidden_size": 2048,
9
  "initializer_range": 0.02,
10
  "intermediate_size": 14336,
11
  "max_position_embeddings": 131072,
12
  "model_type": "mistral",
13
  "num_attention_heads": 32,
14
- "num_hidden_layers": 32,
15
  "num_key_value_heads": 8,
16
- "rms_norm_eps": 1e-06,
17
  "rope_theta": 10000.0,
18
  "sliding_window": 4096,
19
  "tie_word_embeddings": false,
20
- "torch_dtype": "bfloat16",
21
- "transformers_version": "4.35.0.dev0",
22
- "use_cache": true,
23
  "vocab_size": 32000
24
  }
 
1
  {
2
+ "_name_or_path": "typeof/mistral-3b",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 14336,
12
  "max_position_embeddings": 131072,
13
  "model_type": "mistral",
14
  "num_attention_heads": 32,
15
+ "num_hidden_layers": 14,
16
  "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
  "rope_theta": 10000.0,
19
  "sliding_window": 4096,
20
  "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.36.0.dev0",
23
+ "use_cache": false,
24
  "vocab_size": 32000
25
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.35.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.36.0.dev0"
6
  }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72255c230a76633b9e09f812474382447cf11a491a1228d4be8dd66f884e6a01
3
+ size 1889587008
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538b689a695473ab32d9251f512044ba97c43eb2720b963956f73ee884928559
3
+ size 1946243896
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2864861cd77dd1d7d411022e12e97aae09096962df9c603b15e796dbd79d2b80
3
+ size 1979781392
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9dbe322aa3fdc9daa0ab700f740d6ea2b8f105b5e15bd4cddebfc0878e1ae3
3
+ size 815834664
model.safetensors.index.json CHANGED
@@ -1,298 +1,136 @@
1
  {
2
  "metadata": {
3
- "total_size": 6570643456
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_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
- "model.norm.weight": "model-00002-of-00002.safetensors"
297
  }
298
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 6631432192
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-00003-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
62
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
63
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
64
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
65
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
66
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
67
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
68
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
69
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
70
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
71
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
74
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
75
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
77
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
78
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
79
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
80
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.norm.weight": "model-00004-of-00004.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  }
136
  }
special_tokens_map.json CHANGED
@@ -18,6 +18,13 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
 
 
 
 
 
 
 
21
  "unk_token": {
22
  "content": "<unk>",
23
  "lstrip": false,
 
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
+ "pad_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
  "unk_token": {
29
  "content": "<unk>",
30
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
@@ -31,14 +33,20 @@
31
  "</s>"
32
  ],
33
  "bos_token": "<s>",
 
34
  "clean_up_tokenization_spaces": false,
35
  "eos_token": "</s>",
36
  "legacy": true,
 
37
  "model_max_length": 1000000000000000019884624838656,
38
- "pad_token": null,
 
39
  "sp_model_kwargs": {},
40
  "spaces_between_special_tokens": false,
 
41
  "tokenizer_class": "LlamaTokenizer",
 
 
42
  "unk_token": "<unk>",
43
  "use_default_system_prompt": true
44
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
33
  "</s>"
34
  ],
35
  "bos_token": "<s>",
36
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
  "legacy": true,
40
+ "max_length": 512,
41
  "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<unk>",
43
+ "padding_side": "right",
44
  "sp_model_kwargs": {},
45
  "spaces_between_special_tokens": false,
46
+ "stride": 0,
47
  "tokenizer_class": "LlamaTokenizer",
48
+ "truncation_side": "right",
49
+ "truncation_strategy": "longest_first",
50
  "unk_token": "<unk>",
51
  "use_default_system_prompt": true
52
  }