ybelkada commited on
Commit
25c14ec
1 Parent(s): 0e991a8

Upload model

Browse files
Files changed (2) hide show
  1. config.json +206 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "ClapModel"
5
+ ],
6
+ "audio_config": {
7
+ "_name_or_path": "",
8
+ "add_cross_attention": false,
9
+ "aff_block_r": 4,
10
+ "architectures": null,
11
+ "attention_probs_dropout_prob": 0.0,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "depths": [
19
+ 2,
20
+ 2,
21
+ 6,
22
+ 2
23
+ ],
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "drop_path_rate": 0.0,
27
+ "early_stopping": false,
28
+ "enable_fusion": false,
29
+ "enable_patch_layer_norm": true,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": null,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "flatten_patch_embeds": true,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "fusion_num_hidden_layers": 2,
38
+ "fusion_type": null,
39
+ "hidden_act": "gelu",
40
+ "hidden_dropout_prob": 0.1,
41
+ "hidden_size": 768,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_factor": 1.0,
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "layer_norm_eps": 1e-05,
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "min_length": 0,
57
+ "mlp_ratio": 4.0,
58
+ "model_type": "clap_audio_model",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_attention_heads": [
61
+ 4,
62
+ 8,
63
+ 16,
64
+ 32
65
+ ],
66
+ "num_beam_groups": 1,
67
+ "num_beams": 1,
68
+ "num_classes": 527,
69
+ "num_hidden_layers": 4,
70
+ "num_mel_bins": 64,
71
+ "num_return_sequences": 1,
72
+ "output_attentions": false,
73
+ "output_hidden_states": false,
74
+ "output_scores": false,
75
+ "pad_token_id": null,
76
+ "patch_embed_input_channels": 1,
77
+ "patch_embeds_hidden_size": 96,
78
+ "patch_size": 4,
79
+ "patch_stride": [
80
+ 4,
81
+ 4
82
+ ],
83
+ "prefix": null,
84
+ "problem_type": null,
85
+ "projection_dim": 512,
86
+ "projection_hidden_act": "relu",
87
+ "projection_hidden_size": 768,
88
+ "pruned_heads": {},
89
+ "qkv_bias": true,
90
+ "remove_invalid_values": false,
91
+ "repetition_penalty": 1.0,
92
+ "return_dict": true,
93
+ "return_dict_in_generate": false,
94
+ "sep_token_id": null,
95
+ "spec_size": 256,
96
+ "suppress_tokens": null,
97
+ "task_specific_params": null,
98
+ "temperature": 1.0,
99
+ "tf_legacy_loss": false,
100
+ "tie_encoder_decoder": false,
101
+ "tie_word_embeddings": true,
102
+ "tokenizer_class": null,
103
+ "top_k": 50,
104
+ "top_p": 1.0,
105
+ "torch_dtype": null,
106
+ "torchscript": false,
107
+ "transformers_version": "4.27.0.dev0",
108
+ "typical_p": 1.0,
109
+ "use_bfloat16": false,
110
+ "window_size": 8
111
+ },
112
+ "hidden_size": 768,
113
+ "initializer_factor": 1.0,
114
+ "logit_scale_init_value": 14.285714285714285,
115
+ "model_type": "clap",
116
+ "num_hidden_layers": 16,
117
+ "projection_dim": 512,
118
+ "projection_hidden_act": "relu",
119
+ "text_config": {
120
+ "_name_or_path": "",
121
+ "add_cross_attention": false,
122
+ "architectures": null,
123
+ "attention_probs_dropout_prob": 0.1,
124
+ "bad_words_ids": null,
125
+ "begin_suppress_tokens": null,
126
+ "bos_token_id": 0,
127
+ "chunk_size_feed_forward": 0,
128
+ "classifier_dropout": null,
129
+ "cross_attention_hidden_size": null,
130
+ "decoder_start_token_id": null,
131
+ "diversity_penalty": 0.0,
132
+ "do_sample": false,
133
+ "early_stopping": false,
134
+ "encoder_no_repeat_ngram_size": 0,
135
+ "eos_token_id": 2,
136
+ "exponential_decay_length_penalty": null,
137
+ "finetuning_task": null,
138
+ "forced_bos_token_id": null,
139
+ "forced_eos_token_id": null,
140
+ "fusion_hidden_size": 768,
141
+ "fusion_num_hidden_layers": 2,
142
+ "hidden_act": "gelu",
143
+ "hidden_dropout_prob": 0.1,
144
+ "hidden_size": 768,
145
+ "id2label": {
146
+ "0": "LABEL_0",
147
+ "1": "LABEL_1"
148
+ },
149
+ "initializer_factor": 1.0,
150
+ "initializer_range": 0.02,
151
+ "intermediate_size": 3072,
152
+ "is_decoder": false,
153
+ "is_encoder_decoder": false,
154
+ "label2id": {
155
+ "LABEL_0": 0,
156
+ "LABEL_1": 1
157
+ },
158
+ "layer_norm_eps": 1e-12,
159
+ "length_penalty": 1.0,
160
+ "max_length": 20,
161
+ "max_position_embeddings": 514,
162
+ "min_length": 0,
163
+ "model_type": "clap_text_model",
164
+ "no_repeat_ngram_size": 0,
165
+ "num_attention_heads": 12,
166
+ "num_beam_groups": 1,
167
+ "num_beams": 1,
168
+ "num_hidden_layers": 12,
169
+ "num_return_sequences": 1,
170
+ "output_attentions": false,
171
+ "output_hidden_states": false,
172
+ "output_scores": false,
173
+ "pad_token_id": 1,
174
+ "position_embedding_type": "absolute",
175
+ "prefix": null,
176
+ "problem_type": null,
177
+ "projection_dim": 512,
178
+ "projection_hidden_act": "relu",
179
+ "projection_hidden_size": 768,
180
+ "pruned_heads": {},
181
+ "remove_invalid_values": false,
182
+ "repetition_penalty": 1.0,
183
+ "return_dict": true,
184
+ "return_dict_in_generate": false,
185
+ "sep_token_id": null,
186
+ "suppress_tokens": null,
187
+ "task_specific_params": null,
188
+ "temperature": 1.0,
189
+ "tf_legacy_loss": false,
190
+ "tie_encoder_decoder": false,
191
+ "tie_word_embeddings": true,
192
+ "tokenizer_class": null,
193
+ "top_k": 50,
194
+ "top_p": 1.0,
195
+ "torch_dtype": null,
196
+ "torchscript": false,
197
+ "transformers_version": "4.27.0.dev0",
198
+ "type_vocab_size": 1,
199
+ "typical_p": 1.0,
200
+ "use_bfloat16": false,
201
+ "use_cache": true,
202
+ "vocab_size": 50265
203
+ },
204
+ "torch_dtype": "float32",
205
+ "transformers_version": null
206
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd3c601bc4afe0fa87be3de4c13dd2cfadd249fac1e29acf74a9b296c3219bb
3
+ size 614525833