shanearora commited on
Commit
62dcbf0
1 Parent(s): 1856db8

upload checkpoint

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Olmo1124ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 100257,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "olmo_1124",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 100277,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_scaling": null,
20
+ "rope_theta": 500000,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.47.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 100352
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 100257,
4
+ "pad_token_id": 100277,
5
+ "transformers_version": "4.47.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a79348b25026907e58971b6df7178a425bc0c8fc5d97d3a4f6afe55a3e269cd
3
+ size 4949546184
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492c0157b0434fc81da7c4bf7529483860700568c0563af50cf4e60f024c3a4a
3
+ size 4991622816
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2008df8608a595e31b343bbf0a6eec82129cfa72300022cad67e3d2a8f37bcf3
3
+ size 4924546896
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca467a431864280584b7ecd7bf4b48f3c662398ba6811997c31dcd3f310f8f0f
3
+ size 4857404928
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f543e2414e72fecbf9a99d100932921c3f1a5e216cc97b2ce976f5d0ae83b68
3
+ size 4857404928
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8aaf54602f35f74050910902b2d328f8c7f6a1e0fecb06e354fbbb8f0cc9f0e
3
+ size 4613984792
model.safetensors.index.json ADDED
@@ -0,0 +1,362 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29194469376
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.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.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.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
31
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
32
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
34
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
118
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
119
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
120
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
121
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
122
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
141
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
142
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
144
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
151
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
155
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
162
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
163
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
165
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
166
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
195
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
196
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
197
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
198
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
199
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
206
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
207
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
208
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
209
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
210
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
217
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
218
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
219
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
220
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
221
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
228
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
229
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
230
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
231
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
232
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
239
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
240
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
241
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
242
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
243
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
251
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
252
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
253
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
254
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
265
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
272
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
273
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
274
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
275
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
276
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
283
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
284
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
285
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
286
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
287
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
294
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
295
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
296
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
297
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
298
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
299
+ "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
300
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
301
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
302
+ "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
303
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
304
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
305
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
306
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
307
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
308
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
309
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
310
+ "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
311
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
312
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
313
+ "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
314
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
315
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
316
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
317
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
318
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
319
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
320
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
321
+ "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
322
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
323
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
324
+ "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
325
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
326
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
327
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
328
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
329
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
330
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
331
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
332
+ "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
333
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
334
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
335
+ "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
336
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
337
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
338
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
339
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
340
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
341
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
342
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
343
+ "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
344
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
345
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
346
+ "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
347
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
348
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
349
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
350
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
351
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
352
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
353
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
354
+ "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
355
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
356
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
357
+ "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
358
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
359
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
360
+ "model.norm.weight": "model-00006-of-00006.safetensors"
361
+ }
362
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|pad|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|extra_id_0|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "|||PHONE_NUMBER|||",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "100262": {
53
+ "content": "|||EMAIL_ADDRESS|||",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "100263": {
61
+ "content": "|||IP_ADDRESS|||",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "100264": {
69
+ "content": "<|im_start|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|im_end|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|extra_id_1|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "100267": {
93
+ "content": "<|extra_id_2|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "100268": {
101
+ "content": "<|extra_id_3|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "100269": {
109
+ "content": "<|extra_id_4|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "100270": {
117
+ "content": "<|extra_id_5|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "100271": {
125
+ "content": "<|extra_id_6|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "100272": {
133
+ "content": "<|extra_id_7|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "100273": {
141
+ "content": "<|extra_id_8|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "100274": {
149
+ "content": "<|extra_id_9|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "100275": {
157
+ "content": "<|extra_id_10|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100277": {
173
+ "content": "<|pad|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ }
180
+ },
181
+ "bos_token": "<|endoftext|>",
182
+ "clean_up_tokenization_spaces": false,
183
+ "eos_token": "<|endoftext|>",
184
+ "extra_special_tokens": {},
185
+ "model_max_length": 1000000000000000019884624838656,
186
+ "pad_token": "<|pad|>",
187
+ "tokenizer_class": "GPT2Tokenizer",
188
+ "unk_token": "<|endoftext|>"
189
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff