Hugging Face's logo

facebook
/
pe-a-frame-small

Safetensors
pe_audio
Model card Files
xet
Community
1
lematt1991 commited on
Commit
9796e26
·
verified ·
1 Parent(s): 4c99b6c

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +18 -200
  2. model.safetensors +2 -2
  3. preprocessor_config.json +1 -1
config.json CHANGED
@@ -1,103 +1,22 @@
1
  {
2
- "audio_model": {
3
- "transformer": {
4
- "vocab_size": 151936,
5
- "max_position_embeddings": 10000,
6
- "hidden_size": 768,
7
- "intermediate_size": 2048,
8
- "num_hidden_layers": 12,
9
- "num_attention_heads": 6,
10
- "use_sliding_window": false,
11
- "sliding_window": null,
12
- "max_window_layers": 28,
13
- "num_key_value_heads": 6,
14
- "head_dim": 128,
15
- "hidden_act": "silu",
16
- "initializer_range": 0.02,
17
- "rms_norm_eps": 1e-05,
18
- "use_cache": true,
19
- "rope_theta": 20000,
20
- "rope_scaling": null,
21
- "attention_bias": false,
22
- "attention_dropout": 0.0,
23
- "layer_types": [
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention"
36
- ],
37
- "return_dict": true,
38
- "output_hidden_states": false,
39
- "torchscript": false,
40
- "dtype": null,
41
- "pruned_heads": {},
42
- "tie_word_embeddings": false,
43
- "chunk_size_feed_forward": 0,
44
- "is_encoder_decoder": false,
45
- "is_decoder": false,
46
- "cross_attention_hidden_size": null,
47
- "add_cross_attention": false,
48
- "tie_encoder_decoder": false,
49
- "architectures": null,
50
- "finetuning_task": null,
51
- "id2label": {
52
- "0": "LABEL_0",
53
- "1": "LABEL_1"
54
- },
55
- "label2id": {
56
- "LABEL_0": 0,
57
- "LABEL_1": 1
58
- },
59
- "task_specific_params": null,
60
- "problem_type": null,
61
- "tokenizer_class": null,
62
- "prefix": null,
63
- "bos_token_id": null,
64
- "pad_token_id": null,
65
- "eos_token_id": null,
66
- "sep_token_id": null,
67
- "decoder_start_token_id": null,
68
- "max_length": 20,
69
- "min_length": 0,
70
- "do_sample": false,
71
- "early_stopping": false,
72
- "num_beams": 1,
73
- "temperature": 1.0,
74
- "top_k": 50,
75
- "top_p": 1.0,
76
- "typical_p": 1.0,
77
- "repetition_penalty": 1.0,
78
- "length_penalty": 1.0,
79
- "no_repeat_ngram_size": 0,
80
- "encoder_no_repeat_ngram_size": 0,
81
- "bad_words_ids": null,
82
- "num_return_sequences": 1,
83
- "output_scores": false,
84
- "return_dict_in_generate": false,
85
- "forced_bos_token_id": null,
86
- "forced_eos_token_id": null,
87
- "remove_invalid_values": false,
88
- "exponential_decay_length_penalty": null,
89
- "suppress_tokens": null,
90
- "begin_suppress_tokens": null,
91
- "num_beam_groups": 1,
92
- "diversity_penalty": 0.0,
93
- "_name_or_path": "",
94
- "transformers_version": "4.57.0.dev0",
95
- "tf_legacy_loss": false,
96
- "use_bfloat16": false,
97
- "model_type": "qwen3",
98
- "output_attentions": false
99
  },
100
- "dac_vae_encoder": {
 
 
101
  "encoder_hidden_size": 64,
102
  "downsampling_ratios": [
103
  2,
@@ -112,106 +31,5 @@
112
  "quantizer_dropout": 0,
113
  "sampling_rate": 48000
114
  }
115
- },
116
- "text_model": {
117
- "return_dict": true,
118
- "output_hidden_states": false,
119
- "torchscript": false,
120
- "dtype": "float32",
121
- "pruned_heads": {},
122
- "tie_word_embeddings": true,
123
- "chunk_size_feed_forward": 0,
124
- "is_encoder_decoder": false,
125
- "is_decoder": false,
126
- "cross_attention_hidden_size": null,
127
- "add_cross_attention": false,
128
- "tie_encoder_decoder": false,
129
- "architectures": [
130
- "ModernBertForMaskedLM"
131
- ],
132
- "finetuning_task": null,
133
- "id2label": {
134
- "0": "LABEL_0",
135
- "1": "LABEL_1"
136
- },
137
- "label2id": {
138
- "LABEL_0": 0,
139
- "LABEL_1": 1
140
- },
141
- "task_specific_params": null,
142
- "problem_type": null,
143
- "tokenizer_class": null,
144
- "prefix": null,
145
- "bos_token_id": 50281,
146
- "pad_token_id": 50283,
147
- "eos_token_id": 50282,
148
- "sep_token_id": 50282,
149
- "decoder_start_token_id": null,
150
- "max_length": 20,
151
- "min_length": 0,
152
- "do_sample": false,
153
- "early_stopping": false,
154
- "num_beams": 1,
155
- "temperature": 1.0,
156
- "top_k": 50,
157
- "top_p": 1.0,
158
- "typical_p": 1.0,
159
- "repetition_penalty": 1.0,
160
- "length_penalty": 1.0,
161
- "no_repeat_ngram_size": 0,
162
- "encoder_no_repeat_ngram_size": 0,
163
- "bad_words_ids": null,
164
- "num_return_sequences": 1,
165
- "output_scores": false,
166
- "return_dict_in_generate": false,
167
- "forced_bos_token_id": null,
168
- "forced_eos_token_id": null,
169
- "remove_invalid_values": false,
170
- "exponential_decay_length_penalty": null,
171
- "suppress_tokens": null,
172
- "begin_suppress_tokens": null,
173
- "num_beam_groups": 1,
174
- "diversity_penalty": 0.0,
175
- "_name_or_path": "answerdotai/ModernBERT-large",
176
- "transformers_version": "4.57.0.dev0",
177
- "cls_token_id": 50281,
178
- "gradient_checkpointing": false,
179
- "layer_norm_eps": 1e-05,
180
- "model_type": "modernbert",
181
- "position_embedding_type": "absolute",
182
- "tf_legacy_loss": false,
183
- "use_bfloat16": false,
184
- "vocab_size": 50368,
185
- "max_position_embeddings": 8192,
186
- "hidden_size": 1024,
187
- "intermediate_size": 2624,
188
- "num_hidden_layers": 28,
189
- "num_attention_heads": 16,
190
- "initializer_range": 0.02,
191
- "initializer_cutoff_factor": 2.0,
192
- "norm_eps": 1e-05,
193
- "norm_bias": false,
194
- "global_rope_theta": 160000.0,
195
- "attention_bias": false,
196
- "attention_dropout": 0.0,
197
- "hidden_activation": "gelu",
198
- "global_attn_every_n_layers": 3,
199
- "local_attention": 128,
200
- "local_rope_theta": 10000.0,
201
- "embedding_dropout": 0.0,
202
- "mlp_bias": false,
203
- "mlp_dropout": 0.0,
204
- "decoder_bias": true,
205
- "classifier_pooling": "mean",
206
- "classifier_dropout": 0.0,
207
- "classifier_bias": false,
208
- "classifier_activation": "gelu",
209
- "deterministic_flash_attn": false,
210
- "sparse_prediction": false,
211
- "sparse_pred_ignore_index": -100,
212
- "repad_logits_with_grad": false,
213
- "output_attentions": false
214
- },
215
- "output_dim": 1024,
216
- "nth_text_layer": 22
217
  }
 
1
  {
2
+ "model_type": "pe_audio_frame",
3
+ "audio_config": {
4
+ "hidden_size": 768,
5
+ "intermediate_size": 2048,
6
+ "num_hidden_layers": 12,
7
+ "num_attention_heads": 6,
8
+ "head_dim": 128,
9
+ "num_key_value_heads": null,
10
+ "hidden_act": "silu",
11
+ "max_position_embeddings": 10000,
12
+ "initializer_range": 0.02,
13
+ "rms_norm_eps": 1e-05,
14
+ "rope_parameters": {
15
+ "rope_theta": 20000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  },
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "dac_config": {
20
  "encoder_hidden_size": 64,
21
  "downsampling_ratios": [
22
  2,
 
31
  "quantizer_dropout": 0,
32
  "sampling_rate": 48000
33
  }
34
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a62a9bdef851a0f77c6a0117b427b77395107fbaac1e9af539a0cd49d5a0e23
3
- size 2053989872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662e83876d650d6775ba26bab2053aec7711956c19bb59574ae9018357f7ee07
3
+ size 1759281224
preprocessor_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "feature_extractor_type": "PEAudioVideoFeatureExtractor",
3
  "feature_size": 1,
4
  "hop_length": 1920,
5
  "padding_side": "right",
 
1
  {
2
+ "feature_extractor_type": "PeAudioFeatureExtractor",
3
  "feature_size": 1,
4
  "hop_length": 1920,
5
  "padding_side": "right",