winglian commited on
Commit
4706a32
1 Parent(s): a65ba9c

Upload GemmaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../axolotl/out/merged/",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 18,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.38.1",
26
+ "use_cache": false,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "do_sample": true,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.38.1"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3e4f726fbb04d78a29e631e1bb06b5971ef2e7f5935c8186903d460c151515
3
+ size 4945242264
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320dc34653ea241c89deda8057a617c0f0f9a65042704262f52a58376b383639
3
+ size 67121608
model.safetensors.index.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.norm.weight": "model-00002-of-00002.safetensors"
170
+ }
171
+ }