sebaweis commited on
Commit
cff0041
1 Parent(s): 0cb5c5d

Upload model

Browse files
config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alibi": false,
4
  "apply_residual_connection_post_layernorm": false,
5
  "architectures": [
6
- "RWForCausalLM"
7
  ],
8
  "attention_dropout": 0.0,
9
  "auto_map": {
@@ -26,17 +26,6 @@
26
  "n_head": 71,
27
  "n_layer": 32,
28
  "parallel_attn": true,
29
- "quantization_config": {
30
- "bnb_4bit_compute_dtype": "float16",
31
- "bnb_4bit_quant_type": "nf4",
32
- "bnb_4bit_use_double_quant": true,
33
- "llm_int8_enable_fp32_cpu_offload": false,
34
- "llm_int8_has_fp16_weight": false,
35
- "llm_int8_skip_modules": null,
36
- "llm_int8_threshold": 6.0,
37
- "load_in_4bit": false,
38
- "load_in_8bit": true
39
- },
40
  "torch_dtype": "float16",
41
  "transformers_version": "4.31.0.dev0",
42
  "use_cache": true,
 
3
  "alibi": false,
4
  "apply_residual_connection_post_layernorm": false,
5
  "architectures": [
6
+ "RWModel"
7
  ],
8
  "attention_dropout": 0.0,
9
  "auto_map": {
 
26
  "n_head": 71,
27
  "n_layer": 32,
28
  "parallel_attn": true,
 
 
 
 
 
 
 
 
 
 
 
29
  "torch_dtype": "float16",
30
  "transformers_version": "4.31.0.dev0",
31
  "use_cache": true,
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfff9b8566052f545c7dfa4b205d232e379895c302b2a4133857b665dc0293f9
3
+ size 9951026529
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff80eaf11240587ffe4ca44b23fff07bb393f7ee2a3c8b7a150da365d5f044a
3
+ size 3892482449
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13843441408
4
+ },
5
+ "weight_map": {
6
+ "h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
7
+ "h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
8
+ "h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
9
+ "h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
10
+ "h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
11
+ "h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
12
+ "h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
13
+ "h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
+ "h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
15
+ "h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
16
+ "h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
17
+ "h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
18
+ "h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
19
+ "h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
20
+ "h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
21
+ "h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
22
+ "h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
23
+ "h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
24
+ "h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
25
+ "h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
27
+ "h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
28
+ "h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
29
+ "h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
30
+ "h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
31
+ "h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
32
+ "h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
33
+ "h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
34
+ "h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
35
+ "h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
36
+ "h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
37
+ "h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
38
+ "h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
39
+ "h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
40
+ "h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
41
+ "h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
42
+ "h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
43
+ "h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
44
+ "h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
45
+ "h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
46
+ "h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
47
+ "h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
48
+ "h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
49
+ "h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
50
+ "h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
51
+ "h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
52
+ "h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
53
+ "h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
54
+ "h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
55
+ "h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
56
+ "h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
57
+ "h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
58
+ "h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
59
+ "h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
60
+ "h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
61
+ "h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
63
+ "h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
64
+ "h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
65
+ "h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
66
+ "h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
67
+ "h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
68
+ "h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
69
+ "h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
70
+ "h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
71
+ "h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
72
+ "h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
73
+ "h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
74
+ "h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
75
+ "h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
76
+ "h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
77
+ "h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
78
+ "h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
79
+ "h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
81
+ "h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
82
+ "h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
83
+ "h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
84
+ "h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
85
+ "h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
86
+ "h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
87
+ "h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
88
+ "h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
89
+ "h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
90
+ "h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
91
+ "h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
92
+ "h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
93
+ "h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
94
+ "h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
95
+ "h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
96
+ "h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
97
+ "h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
99
+ "h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
100
+ "h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
101
+ "h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
102
+ "h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
103
+ "h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
104
+ "h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
105
+ "h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
106
+ "h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
107
+ "h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
108
+ "h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
109
+ "h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
110
+ "h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
111
+ "h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
112
+ "h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
113
+ "h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
114
+ "h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
115
+ "h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
116
+ "h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
117
+ "h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
118
+ "h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
119
+ "h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
120
+ "h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
121
+ "h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
122
+ "h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
123
+ "h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
124
+ "h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
125
+ "h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
126
+ "h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
127
+ "h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
128
+ "h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
129
+ "h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
130
+ "h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
131
+ "h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
132
+ "h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
133
+ "h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
134
+ "h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
135
+ "h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
136
+ "h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
137
+ "h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
138
+ "h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
139
+ "h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
140
+ "h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
141
+ "h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
142
+ "h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
143
+ "h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
144
+ "h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
145
+ "h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
146
+ "h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
147
+ "h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
148
+ "h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
149
+ "h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
150
+ "h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
151
+ "h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
152
+ "h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
153
+ "h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
154
+ "h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
155
+ "h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
156
+ "h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
157
+ "h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
158
+ "h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
159
+ "h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
160
+ "h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
161
+ "h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
162
+ "h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
163
+ "h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
164
+ "h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
165
+ "h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
166
+ "h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
167
+ "h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
168
+ "h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
169
+ "h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
170
+ "h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
171
+ "h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
172
+ "h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
173
+ "h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
174
+ "h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
175
+ "h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
176
+ "h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
177
+ "h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
178
+ "h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
179
+ "h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
180
+ "h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
181
+ "h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
182
+ "h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
183
+ "h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
184
+ "h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
185
+ "h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
186
+ "h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
187
+ "h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
188
+ "h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
189
+ "h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
190
+ "h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
191
+ "h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
192
+ "h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
193
+ "h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
194
+ "h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
195
+ "h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
196
+ "h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
197
+ "h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
198
+ "ln_f.bias": "pytorch_model-00002-of-00002.bin",
199
+ "ln_f.weight": "pytorch_model-00002-of-00002.bin",
200
+ "word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
201
+ }
202
+ }