ssmits commited on
Commit
223833c
1 Parent(s): 2a0c07a

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ssmits/Falcon2-5.5B-multilingual",
3
+ "activation": "gelu",
4
+ "alibi": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "ff_factor": 4,
21
+ "ffn_hidden_size": 16384,
22
+ "hidden_dropout": 0.0,
23
+ "hidden_size": 4096,
24
+ "initializer_range": 0.02,
25
+ "layer_norm_epsilon": 1e-05,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "falcon",
28
+ "multi_query": true,
29
+ "new_decoder_architecture": true,
30
+ "num_attention_heads": 32,
31
+ "num_hidden_layers": 28,
32
+ "num_kv_heads": 8,
33
+ "num_ln_in_parallel_attn": 1,
34
+ "parallel_attn": true,
35
+ "rope_scaling": null,
36
+ "rope_theta": 500042.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.42.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 65024
42
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.42.0.dev0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853591be1a1d1955f957ddd73aa884c025b96221fb61f1966ad6bc44de2a521b
3
+ size 4978844456
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028013902b3c9e15d12ee7194deb8e15cc9a910843fcdebf12bfd5384089e087
3
+ size 4932740888
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5aedbe5caa0fbe962240a38095f0a91078a5d577c94c33cab3944dd2468670
3
+ size 486589656
model.safetensors.index.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10398154752
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
13
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
19
+ "transformer.h.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
21
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
27
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.11.self_attention.dense.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
31
+ "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
32
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
33
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
34
+ "transformer.h.12.self_attention.dense.weight": "model-00001-of-00003.safetensors",
35
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
37
+ "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
38
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
39
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
40
+ "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
41
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
42
+ "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
43
+ "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
45
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
46
+ "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
47
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
48
+ "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
49
+ "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
51
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
52
+ "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
53
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
54
+ "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
55
+ "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
57
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
58
+ "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
59
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
60
+ "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
61
+ "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
63
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
64
+ "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
65
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
66
+ "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
67
+ "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
69
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
70
+ "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
71
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
72
+ "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
73
+ "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
75
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
76
+ "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
77
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
78
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
79
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
81
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
83
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
85
+ "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
89
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
90
+ "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
91
+ "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.h.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
97
+ "transformer.h.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
99
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
103
+ "transformer.h.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
105
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.23.self_attention.dense.weight": "model-00002-of-00003.safetensors",
107
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
109
+ "transformer.h.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
111
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
112
+ "transformer.h.24.self_attention.dense.weight": "model-00002-of-00003.safetensors",
113
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
115
+ "transformer.h.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
116
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
117
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
118
+ "transformer.h.25.self_attention.dense.weight": "model-00002-of-00003.safetensors",
119
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
120
+ "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
121
+ "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
122
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
123
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.26.self_attention.dense.weight": "model-00002-of-00003.safetensors",
125
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
127
+ "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
128
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
129
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
130
+ "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
131
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
132
+ "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
133
+ "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
134
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
135
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
136
+ "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
137
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
138
+ "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
139
+ "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
140
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
141
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
142
+ "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
143
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
144
+ "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
145
+ "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
146
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
147
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
148
+ "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
149
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
150
+ "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
151
+ "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
152
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
153
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
154
+ "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
155
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
156
+ "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
157
+ "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
158
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
159
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
160
+ "transformer.h.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
161
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
162
+ "transformer.h.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
163
+ "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
164
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
165
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
167
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
168
+ "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
169
+ "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
170
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
171
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
172
+ "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
173
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
174
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
175
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
176
+ "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors"
177
+ }
178
+ }