Hugging Face's logo

Tele-AI
/
TeleChat-1B

Text Generation
Transformers
PyTorch
telechat
custom_code
Model card Files
xet
Community
2

Adding `safetensors` variant of this model

#1
by SFconvertbot - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+173
-0
Files changed (2) hide show
  1. model.safetensors.index.json +170 -0
  2. model_00001-of-00001.safetensors +3 -0
model.safetensors.index.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2593656832
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model_00001-of-00001.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model_00001-of-00001.safetensors",
8
+ "transformer.h.0.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
9
+ "transformer.h.0.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
10
+ "transformer.h.0.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
11
+ "transformer.h.0.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
12
+ "transformer.h.0.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
13
+ "transformer.h.0.self_attention.dense.bias": "model_00001-of-00001.safetensors",
14
+ "transformer.h.0.self_attention.dense.weight": "model_00001-of-00001.safetensors",
15
+ "transformer.h.0.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
16
+ "transformer.h.0.self_attention.query.weight": "model_00001-of-00001.safetensors",
17
+ "transformer.h.1.input_layernorm.weight": "model_00001-of-00001.safetensors",
18
+ "transformer.h.1.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
19
+ "transformer.h.1.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
20
+ "transformer.h.1.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
21
+ "transformer.h.1.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
22
+ "transformer.h.1.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
23
+ "transformer.h.1.self_attention.dense.bias": "model_00001-of-00001.safetensors",
24
+ "transformer.h.1.self_attention.dense.weight": "model_00001-of-00001.safetensors",
25
+ "transformer.h.1.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
26
+ "transformer.h.1.self_attention.query.weight": "model_00001-of-00001.safetensors",
27
+ "transformer.h.10.input_layernorm.weight": "model_00001-of-00001.safetensors",
28
+ "transformer.h.10.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
29
+ "transformer.h.10.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
30
+ "transformer.h.10.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
31
+ "transformer.h.10.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
32
+ "transformer.h.10.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
33
+ "transformer.h.10.self_attention.dense.bias": "model_00001-of-00001.safetensors",
34
+ "transformer.h.10.self_attention.dense.weight": "model_00001-of-00001.safetensors",
35
+ "transformer.h.10.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
36
+ "transformer.h.10.self_attention.query.weight": "model_00001-of-00001.safetensors",
37
+ "transformer.h.11.input_layernorm.weight": "model_00001-of-00001.safetensors",
38
+ "transformer.h.11.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
39
+ "transformer.h.11.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
40
+ "transformer.h.11.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
41
+ "transformer.h.11.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
42
+ "transformer.h.11.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
43
+ "transformer.h.11.self_attention.dense.bias": "model_00001-of-00001.safetensors",
44
+ "transformer.h.11.self_attention.dense.weight": "model_00001-of-00001.safetensors",
45
+ "transformer.h.11.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
46
+ "transformer.h.11.self_attention.query.weight": "model_00001-of-00001.safetensors",
47
+ "transformer.h.12.input_layernorm.weight": "model_00001-of-00001.safetensors",
48
+ "transformer.h.12.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
49
+ "transformer.h.12.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
50
+ "transformer.h.12.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
51
+ "transformer.h.12.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
52
+ "transformer.h.12.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
53
+ "transformer.h.12.self_attention.dense.bias": "model_00001-of-00001.safetensors",
54
+ "transformer.h.12.self_attention.dense.weight": "model_00001-of-00001.safetensors",
55
+ "transformer.h.12.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
56
+ "transformer.h.12.self_attention.query.weight": "model_00001-of-00001.safetensors",
57
+ "transformer.h.13.input_layernorm.weight": "model_00001-of-00001.safetensors",
58
+ "transformer.h.13.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
59
+ "transformer.h.13.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
60
+ "transformer.h.13.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
61
+ "transformer.h.13.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
62
+ "transformer.h.13.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
63
+ "transformer.h.13.self_attention.dense.bias": "model_00001-of-00001.safetensors",
64
+ "transformer.h.13.self_attention.dense.weight": "model_00001-of-00001.safetensors",
65
+ "transformer.h.13.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
66
+ "transformer.h.13.self_attention.query.weight": "model_00001-of-00001.safetensors",
67
+ "transformer.h.14.input_layernorm.weight": "model_00001-of-00001.safetensors",
68
+ "transformer.h.14.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
69
+ "transformer.h.14.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
70
+ "transformer.h.14.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
71
+ "transformer.h.14.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
72
+ "transformer.h.14.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
73
+ "transformer.h.14.self_attention.dense.bias": "model_00001-of-00001.safetensors",
74
+ "transformer.h.14.self_attention.dense.weight": "model_00001-of-00001.safetensors",
75
+ "transformer.h.14.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
76
+ "transformer.h.14.self_attention.query.weight": "model_00001-of-00001.safetensors",
77
+ "transformer.h.15.input_layernorm.weight": "model_00001-of-00001.safetensors",
78
+ "transformer.h.15.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
79
+ "transformer.h.15.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
80
+ "transformer.h.15.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
81
+ "transformer.h.15.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
82
+ "transformer.h.15.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
83
+ "transformer.h.15.self_attention.dense.bias": "model_00001-of-00001.safetensors",
84
+ "transformer.h.15.self_attention.dense.weight": "model_00001-of-00001.safetensors",
85
+ "transformer.h.15.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
86
+ "transformer.h.15.self_attention.query.weight": "model_00001-of-00001.safetensors",
87
+ "transformer.h.2.input_layernorm.weight": "model_00001-of-00001.safetensors",
88
+ "transformer.h.2.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
89
+ "transformer.h.2.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
90
+ "transformer.h.2.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
91
+ "transformer.h.2.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
92
+ "transformer.h.2.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
93
+ "transformer.h.2.self_attention.dense.bias": "model_00001-of-00001.safetensors",
94
+ "transformer.h.2.self_attention.dense.weight": "model_00001-of-00001.safetensors",
95
+ "transformer.h.2.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
96
+ "transformer.h.2.self_attention.query.weight": "model_00001-of-00001.safetensors",
97
+ "transformer.h.3.input_layernorm.weight": "model_00001-of-00001.safetensors",
98
+ "transformer.h.3.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
99
+ "transformer.h.3.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
100
+ "transformer.h.3.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
101
+ "transformer.h.3.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
102
+ "transformer.h.3.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
103
+ "transformer.h.3.self_attention.dense.bias": "model_00001-of-00001.safetensors",
104
+ "transformer.h.3.self_attention.dense.weight": "model_00001-of-00001.safetensors",
105
+ "transformer.h.3.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
106
+ "transformer.h.3.self_attention.query.weight": "model_00001-of-00001.safetensors",
107
+ "transformer.h.4.input_layernorm.weight": "model_00001-of-00001.safetensors",
108
+ "transformer.h.4.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
109
+ "transformer.h.4.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
110
+ "transformer.h.4.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
111
+ "transformer.h.4.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
112
+ "transformer.h.4.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
113
+ "transformer.h.4.self_attention.dense.bias": "model_00001-of-00001.safetensors",
114
+ "transformer.h.4.self_attention.dense.weight": "model_00001-of-00001.safetensors",
115
+ "transformer.h.4.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
116
+ "transformer.h.4.self_attention.query.weight": "model_00001-of-00001.safetensors",
117
+ "transformer.h.5.input_layernorm.weight": "model_00001-of-00001.safetensors",
118
+ "transformer.h.5.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
119
+ "transformer.h.5.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
120
+ "transformer.h.5.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
121
+ "transformer.h.5.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
122
+ "transformer.h.5.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
123
+ "transformer.h.5.self_attention.dense.bias": "model_00001-of-00001.safetensors",
124
+ "transformer.h.5.self_attention.dense.weight": "model_00001-of-00001.safetensors",
125
+ "transformer.h.5.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
126
+ "transformer.h.5.self_attention.query.weight": "model_00001-of-00001.safetensors",
127
+ "transformer.h.6.input_layernorm.weight": "model_00001-of-00001.safetensors",
128
+ "transformer.h.6.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
129
+ "transformer.h.6.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
130
+ "transformer.h.6.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
131
+ "transformer.h.6.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
132
+ "transformer.h.6.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
133
+ "transformer.h.6.self_attention.dense.bias": "model_00001-of-00001.safetensors",
134
+ "transformer.h.6.self_attention.dense.weight": "model_00001-of-00001.safetensors",
135
+ "transformer.h.6.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
136
+ "transformer.h.6.self_attention.query.weight": "model_00001-of-00001.safetensors",
137
+ "transformer.h.7.input_layernorm.weight": "model_00001-of-00001.safetensors",
138
+ "transformer.h.7.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
139
+ "transformer.h.7.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
140
+ "transformer.h.7.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
141
+ "transformer.h.7.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
142
+ "transformer.h.7.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
143
+ "transformer.h.7.self_attention.dense.bias": "model_00001-of-00001.safetensors",
144
+ "transformer.h.7.self_attention.dense.weight": "model_00001-of-00001.safetensors",
145
+ "transformer.h.7.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
146
+ "transformer.h.7.self_attention.query.weight": "model_00001-of-00001.safetensors",
147
+ "transformer.h.8.input_layernorm.weight": "model_00001-of-00001.safetensors",
148
+ "transformer.h.8.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
149
+ "transformer.h.8.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
150
+ "transformer.h.8.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
151
+ "transformer.h.8.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
152
+ "transformer.h.8.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
153
+ "transformer.h.8.self_attention.dense.bias": "model_00001-of-00001.safetensors",
154
+ "transformer.h.8.self_attention.dense.weight": "model_00001-of-00001.safetensors",
155
+ "transformer.h.8.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
156
+ "transformer.h.8.self_attention.query.weight": "model_00001-of-00001.safetensors",
157
+ "transformer.h.9.input_layernorm.weight": "model_00001-of-00001.safetensors",
158
+ "transformer.h.9.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
159
+ "transformer.h.9.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
160
+ "transformer.h.9.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
161
+ "transformer.h.9.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
162
+ "transformer.h.9.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
163
+ "transformer.h.9.self_attention.dense.bias": "model_00001-of-00001.safetensors",
164
+ "transformer.h.9.self_attention.dense.weight": "model_00001-of-00001.safetensors",
165
+ "transformer.h.9.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
166
+ "transformer.h.9.self_attention.query.weight": "model_00001-of-00001.safetensors",
167
+ "transformer.ln_f.weight": "model_00001-of-00001.safetensors",
168
+ "transformer.word_embeddings.weight": "model_00001-of-00001.safetensors"
169
+ }
170
+ }
model_00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df3674b84f8651c076d331ead158fae747fce40691a1525f9e84f545d8bc09b
3
+ size 2593675832