ybelkada commited on
Commit
8744556
1 Parent(s): 2c690dd

Upload model

Browse files
Files changed (2) hide show
  1. config.json +207 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
29
+ "enable_patch_fusion": true,
30
+ "enable_patch_layer_norm": true,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "eos_token_id": null,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "flatten_patch_embeds": true,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "fusion_num_hidden_layers": 2,
39
+ "fusion_type": null,
40
+ "hidden_act": "gelu",
41
+ "hidden_dropout_prob": 0.1,
42
+ "hidden_size": 768,
43
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1"
46
+ },
47
+ "initializer_factor": 1.0,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "layer_norm_eps": 1e-05,
55
+ "length_penalty": 1.0,
56
+ "max_length": 20,
57
+ "min_length": 0,
58
+ "mlp_ratio": 4.0,
59
+ "model_type": "clap_audio_model",
60
+ "no_repeat_ngram_size": 0,
61
+ "num_attention_heads": [
62
+ 4,
63
+ 8,
64
+ 16,
65
+ 32
66
+ ],
67
+ "num_beam_groups": 1,
68
+ "num_beams": 1,
69
+ "num_classes": 527,
70
+ "num_hidden_layers": 4,
71
+ "num_mel_bins": 64,
72
+ "num_return_sequences": 1,
73
+ "output_attentions": false,
74
+ "output_hidden_states": false,
75
+ "output_scores": false,
76
+ "pad_token_id": null,
77
+ "patch_embed_input_channels": 1,
78
+ "patch_embeds_hidden_size": 96,
79
+ "patch_size": 4,
80
+ "patch_stride": [
81
+ 4,
82
+ 4
83
+ ],
84
+ "prefix": null,
85
+ "problem_type": null,
86
+ "projection_dim": 512,
87
+ "projection_hidden_act": "relu",
88
+ "projection_hidden_size": 768,
89
+ "pruned_heads": {},
90
+ "qkv_bias": true,
91
+ "remove_invalid_values": false,
92
+ "repetition_penalty": 1.0,
93
+ "return_dict": true,
94
+ "return_dict_in_generate": false,
95
+ "sep_token_id": null,
96
+ "spec_size": 256,
97
+ "suppress_tokens": null,
98
+ "task_specific_params": null,
99
+ "temperature": 1.0,
100
+ "tf_legacy_loss": false,
101
+ "tie_encoder_decoder": false,
102
+ "tie_word_embeddings": true,
103
+ "tokenizer_class": null,
104
+ "top_k": 50,
105
+ "top_p": 1.0,
106
+ "torch_dtype": null,
107
+ "torchscript": false,
108
+ "transformers_version": "4.27.0.dev0",
109
+ "typical_p": 1.0,
110
+ "use_bfloat16": false,
111
+ "window_size": 8
112
+ },
113
+ "hidden_size": 768,
114
+ "initializer_factor": 1.0,
115
+ "logit_scale_init_value": 14.285714285714285,
116
+ "model_type": "clap",
117
+ "num_hidden_layers": 16,
118
+ "projection_dim": 512,
119
+ "projection_hidden_act": "relu",
120
+ "text_config": {
121
+ "_name_or_path": "",
122
+ "add_cross_attention": false,
123
+ "architectures": null,
124
+ "attention_probs_dropout_prob": 0.1,
125
+ "bad_words_ids": null,
126
+ "begin_suppress_tokens": null,
127
+ "bos_token_id": 0,
128
+ "chunk_size_feed_forward": 0,
129
+ "classifier_dropout": null,
130
+ "cross_attention_hidden_size": null,
131
+ "decoder_start_token_id": null,
132
+ "diversity_penalty": 0.0,
133
+ "do_sample": false,
134
+ "early_stopping": false,
135
+ "encoder_no_repeat_ngram_size": 0,
136
+ "eos_token_id": 2,
137
+ "exponential_decay_length_penalty": null,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "fusion_hidden_size": 768,
142
+ "fusion_num_hidden_layers": 2,
143
+ "hidden_act": "gelu",
144
+ "hidden_dropout_prob": 0.1,
145
+ "hidden_size": 768,
146
+ "id2label": {
147
+ "0": "LABEL_0",
148
+ "1": "LABEL_1"
149
+ },
150
+ "initializer_factor": 1.0,
151
+ "initializer_range": 0.02,
152
+ "intermediate_size": 3072,
153
+ "is_decoder": false,
154
+ "is_encoder_decoder": false,
155
+ "label2id": {
156
+ "LABEL_0": 0,
157
+ "LABEL_1": 1
158
+ },
159
+ "layer_norm_eps": 1e-12,
160
+ "length_penalty": 1.0,
161
+ "max_length": 20,
162
+ "max_position_embeddings": 514,
163
+ "min_length": 0,
164
+ "model_type": "clap_text_model",
165
+ "no_repeat_ngram_size": 0,
166
+ "num_attention_heads": 12,
167
+ "num_beam_groups": 1,
168
+ "num_beams": 1,
169
+ "num_hidden_layers": 12,
170
+ "num_return_sequences": 1,
171
+ "output_attentions": false,
172
+ "output_hidden_states": false,
173
+ "output_scores": false,
174
+ "pad_token_id": 1,
175
+ "position_embedding_type": "absolute",
176
+ "prefix": null,
177
+ "problem_type": null,
178
+ "projection_dim": 512,
179
+ "projection_hidden_act": "relu",
180
+ "projection_hidden_size": 768,
181
+ "pruned_heads": {},
182
+ "remove_invalid_values": false,
183
+ "repetition_penalty": 1.0,
184
+ "return_dict": true,
185
+ "return_dict_in_generate": false,
186
+ "sep_token_id": null,
187
+ "suppress_tokens": null,
188
+ "task_specific_params": null,
189
+ "temperature": 1.0,
190
+ "tf_legacy_loss": false,
191
+ "tie_encoder_decoder": false,
192
+ "tie_word_embeddings": true,
193
+ "tokenizer_class": null,
194
+ "top_k": 50,
195
+ "top_p": 1.0,
196
+ "torch_dtype": null,
197
+ "torchscript": false,
198
+ "transformers_version": "4.27.0.dev0",
199
+ "type_vocab_size": 1,
200
+ "typical_p": 1.0,
201
+ "use_bfloat16": false,
202
+ "use_cache": true,
203
+ "vocab_size": 50265
204
+ },
205
+ "torch_dtype": "float32",
206
+ "transformers_version": null
207
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed5d0215d887551ddd0a49ce7311b21429ebdf1e6a129d4e68f743357225253
3
+ size 614596545