Hugging Face's logo

facebook
/
pe-a-frame-large

Safetensors
pe_audio
Model card Files
xet
Community
1
lematt1991 commited on
Commit
97cb636
·
verified ·
1 Parent(s): 1ae9620

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +18 -216
  2. model.safetensors +2 -2
  3. preprocessor_config.json +1 -1
config.json CHANGED
@@ -1,119 +1,22 @@
1
  {
2
- "audio_model": {
3
- "transformer": {
4
- "vocab_size": 151936,
5
- "max_position_embeddings": 10000,
6
- "hidden_size": 1792,
7
- "intermediate_size": 4800,
8
- "num_hidden_layers": 28,
9
- "num_attention_heads": 14,
10
- "use_sliding_window": false,
11
- "sliding_window": null,
12
- "max_window_layers": 28,
13
- "num_key_value_heads": 14,
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
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention"
52
- ],
53
- "return_dict": true,
54
- "output_hidden_states": false,
55
- "torchscript": false,
56
- "dtype": null,
57
- "pruned_heads": {},
58
- "tie_word_embeddings": false,
59
- "chunk_size_feed_forward": 0,
60
- "is_encoder_decoder": false,
61
- "is_decoder": false,
62
- "cross_attention_hidden_size": null,
63
- "add_cross_attention": false,
64
- "tie_encoder_decoder": false,
65
- "architectures": null,
66
- "finetuning_task": null,
67
- "id2label": {
68
- "0": "LABEL_0",
69
- "1": "LABEL_1"
70
- },
71
- "label2id": {
72
- "LABEL_0": 0,
73
- "LABEL_1": 1
74
- },
75
- "task_specific_params": null,
76
- "problem_type": null,
77
- "tokenizer_class": null,
78
- "prefix": null,
79
- "bos_token_id": null,
80
- "pad_token_id": null,
81
- "eos_token_id": null,
82
- "sep_token_id": null,
83
- "decoder_start_token_id": null,
84
- "max_length": 20,
85
- "min_length": 0,
86
- "do_sample": false,
87
- "early_stopping": false,
88
- "num_beams": 1,
89
- "temperature": 1.0,
90
- "top_k": 50,
91
- "top_p": 1.0,
92
- "typical_p": 1.0,
93
- "repetition_penalty": 1.0,
94
- "length_penalty": 1.0,
95
- "no_repeat_ngram_size": 0,
96
- "encoder_no_repeat_ngram_size": 0,
97
- "bad_words_ids": null,
98
- "num_return_sequences": 1,
99
- "output_scores": false,
100
- "return_dict_in_generate": false,
101
- "forced_bos_token_id": null,
102
- "forced_eos_token_id": null,
103
- "remove_invalid_values": false,
104
- "exponential_decay_length_penalty": null,
105
- "suppress_tokens": null,
106
- "begin_suppress_tokens": null,
107
- "num_beam_groups": 1,
108
- "diversity_penalty": 0.0,
109
- "_name_or_path": "",
110
- "transformers_version": "4.57.0.dev0",
111
- "tf_legacy_loss": false,
112
- "use_bfloat16": false,
113
- "model_type": "qwen3",
114
- "output_attentions": false
115
  },
116
- "dac_vae_encoder": {
 
 
117
  "encoder_hidden_size": 64,
118
  "downsampling_ratios": [
119
  2,
@@ -128,106 +31,5 @@
128
  "quantizer_dropout": 0,
129
  "sampling_rate": 48000
130
  }
131
- },
132
- "text_model": {
133
- "return_dict": true,
134
- "output_hidden_states": false,
135
- "torchscript": false,
136
- "dtype": "float32",
137
- "pruned_heads": {},
138
- "tie_word_embeddings": true,
139
- "chunk_size_feed_forward": 0,
140
- "is_encoder_decoder": false,
141
- "is_decoder": false,
142
- "cross_attention_hidden_size": null,
143
- "add_cross_attention": false,
144
- "tie_encoder_decoder": false,
145
- "architectures": [
146
- "ModernBertForMaskedLM"
147
- ],
148
- "finetuning_task": null,
149
- "id2label": {
150
- "0": "LABEL_0",
151
- "1": "LABEL_1"
152
- },
153
- "label2id": {
154
- "LABEL_0": 0,
155
- "LABEL_1": 1
156
- },
157
- "task_specific_params": null,
158
- "problem_type": null,
159
- "tokenizer_class": null,
160
- "prefix": null,
161
- "bos_token_id": 50281,
162
- "pad_token_id": 50283,
163
- "eos_token_id": 50282,
164
- "sep_token_id": 50282,
165
- "decoder_start_token_id": null,
166
- "max_length": 20,
167
- "min_length": 0,
168
- "do_sample": false,
169
- "early_stopping": false,
170
- "num_beams": 1,
171
- "temperature": 1.0,
172
- "top_k": 50,
173
- "top_p": 1.0,
174
- "typical_p": 1.0,
175
- "repetition_penalty": 1.0,
176
- "length_penalty": 1.0,
177
- "no_repeat_ngram_size": 0,
178
- "encoder_no_repeat_ngram_size": 0,
179
- "bad_words_ids": null,
180
- "num_return_sequences": 1,
181
- "output_scores": false,
182
- "return_dict_in_generate": false,
183
- "forced_bos_token_id": null,
184
- "forced_eos_token_id": null,
185
- "remove_invalid_values": false,
186
- "exponential_decay_length_penalty": null,
187
- "suppress_tokens": null,
188
- "begin_suppress_tokens": null,
189
- "num_beam_groups": 1,
190
- "diversity_penalty": 0.0,
191
- "_name_or_path": "answerdotai/ModernBERT-large",
192
- "transformers_version": "4.57.0.dev0",
193
- "cls_token_id": 50281,
194
- "gradient_checkpointing": false,
195
- "layer_norm_eps": 1e-05,
196
- "model_type": "modernbert",
197
- "position_embedding_type": "absolute",
198
- "tf_legacy_loss": false,
199
- "use_bfloat16": false,
200
- "vocab_size": 50368,
201
- "max_position_embeddings": 8192,
202
- "hidden_size": 1024,
203
- "intermediate_size": 2624,
204
- "num_hidden_layers": 28,
205
- "num_attention_heads": 16,
206
- "initializer_range": 0.02,
207
- "initializer_cutoff_factor": 2.0,
208
- "norm_eps": 1e-05,
209
- "norm_bias": false,
210
- "global_rope_theta": 160000.0,
211
- "attention_bias": false,
212
- "attention_dropout": 0.0,
213
- "hidden_activation": "gelu",
214
- "global_attn_every_n_layers": 3,
215
- "local_attention": 128,
216
- "local_rope_theta": 10000.0,
217
- "embedding_dropout": 0.0,
218
- "mlp_bias": false,
219
- "mlp_dropout": 0.0,
220
- "decoder_bias": true,
221
- "classifier_pooling": "mean",
222
- "classifier_dropout": 0.0,
223
- "classifier_bias": false,
224
- "classifier_activation": "gelu",
225
- "deterministic_flash_attn": false,
226
- "sparse_prediction": false,
227
- "sparse_pred_ignore_index": -100,
228
- "repad_logits_with_grad": false,
229
- "output_attentions": false
230
- },
231
- "output_dim": 1024,
232
- "nth_text_layer": 22
233
  }
 
1
  {
2
+ "model_type": "pe_audio_frame",
3
+ "audio_config": {
4
+ "hidden_size": 1792,
5
+ "intermediate_size": 4800,
6
+ "num_hidden_layers": 28,
7
+ "num_attention_heads": 14,
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 sha256:5c49481785935113d6e63b4e08d8e8a2c1b968794f34e3df94900127556170a4
3
- size 6121566960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09564eab252970a482be22fa119ddcc4f445baefcfd171becd73417548296558
3
+ size 5826856520
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",