Hugging Face's logo

facebook
/
pe-a-frame-base

Safetensors
pe_audio
Model card Files
xet
Community
1
lematt1991 commited on
Commit
0ab29d4
·
verified ·
1 Parent(s): 69bd1a0

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +18 -204
  2. model.safetensors +2 -2
  3. preprocessor_config.json +1 -1
config.json CHANGED
@@ -1,107 +1,22 @@
1
  {
2
- "audio_model": {
3
- "transformer": {
4
- "vocab_size": 151936,
5
- "max_position_embeddings": 10000,
6
- "hidden_size": 1024,
7
- "intermediate_size": 2752,
8
- "num_hidden_layers": 16,
9
- "num_attention_heads": 8,
10
- "use_sliding_window": false,
11
- "sliding_window": null,
12
- "max_window_layers": 28,
13
- "num_key_value_heads": 8,
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
- ],
41
- "return_dict": true,
42
- "output_hidden_states": false,
43
- "torchscript": false,
44
- "dtype": null,
45
- "pruned_heads": {},
46
- "tie_word_embeddings": false,
47
- "chunk_size_feed_forward": 0,
48
- "is_encoder_decoder": false,
49
- "is_decoder": false,
50
- "cross_attention_hidden_size": null,
51
- "add_cross_attention": false,
52
- "tie_encoder_decoder": false,
53
- "architectures": null,
54
- "finetuning_task": null,
55
- "id2label": {
56
- "0": "LABEL_0",
57
- "1": "LABEL_1"
58
- },
59
- "label2id": {
60
- "LABEL_0": 0,
61
- "LABEL_1": 1
62
- },
63
- "task_specific_params": null,
64
- "problem_type": null,
65
- "tokenizer_class": null,
66
- "prefix": null,
67
- "bos_token_id": null,
68
- "pad_token_id": null,
69
- "eos_token_id": null,
70
- "sep_token_id": null,
71
- "decoder_start_token_id": null,
72
- "max_length": 20,
73
- "min_length": 0,
74
- "do_sample": false,
75
- "early_stopping": false,
76
- "num_beams": 1,
77
- "temperature": 1.0,
78
- "top_k": 50,
79
- "top_p": 1.0,
80
- "typical_p": 1.0,
81
- "repetition_penalty": 1.0,
82
- "length_penalty": 1.0,
83
- "no_repeat_ngram_size": 0,
84
- "encoder_no_repeat_ngram_size": 0,
85
- "bad_words_ids": null,
86
- "num_return_sequences": 1,
87
- "output_scores": false,
88
- "return_dict_in_generate": false,
89
- "forced_bos_token_id": null,
90
- "forced_eos_token_id": null,
91
- "remove_invalid_values": false,
92
- "exponential_decay_length_penalty": null,
93
- "suppress_tokens": null,
94
- "begin_suppress_tokens": null,
95
- "num_beam_groups": 1,
96
- "diversity_penalty": 0.0,
97
- "_name_or_path": "",
98
- "transformers_version": "4.57.0.dev0",
99
- "tf_legacy_loss": false,
100
- "use_bfloat16": false,
101
- "model_type": "qwen3",
102
- "output_attentions": false
103
  },
104
- "dac_vae_encoder": {
 
 
105
  "encoder_hidden_size": 64,
106
  "downsampling_ratios": [
107
  2,
@@ -116,106 +31,5 @@
116
  "quantizer_dropout": 0,
117
  "sampling_rate": 48000
118
  }
119
- },
120
- "text_model": {
121
- "return_dict": true,
122
- "output_hidden_states": false,
123
- "torchscript": false,
124
- "dtype": "float32",
125
- "pruned_heads": {},
126
- "tie_word_embeddings": true,
127
- "chunk_size_feed_forward": 0,
128
- "is_encoder_decoder": false,
129
- "is_decoder": false,
130
- "cross_attention_hidden_size": null,
131
- "add_cross_attention": false,
132
- "tie_encoder_decoder": false,
133
- "architectures": [
134
- "ModernBertForMaskedLM"
135
- ],
136
- "finetuning_task": null,
137
- "id2label": {
138
- "0": "LABEL_0",
139
- "1": "LABEL_1"
140
- },
141
- "label2id": {
142
- "LABEL_0": 0,
143
- "LABEL_1": 1
144
- },
145
- "task_specific_params": null,
146
- "problem_type": null,
147
- "tokenizer_class": null,
148
- "prefix": null,
149
- "bos_token_id": 50281,
150
- "pad_token_id": 50283,
151
- "eos_token_id": 50282,
152
- "sep_token_id": 50282,
153
- "decoder_start_token_id": null,
154
- "max_length": 20,
155
- "min_length": 0,
156
- "do_sample": false,
157
- "early_stopping": false,
158
- "num_beams": 1,
159
- "temperature": 1.0,
160
- "top_k": 50,
161
- "top_p": 1.0,
162
- "typical_p": 1.0,
163
- "repetition_penalty": 1.0,
164
- "length_penalty": 1.0,
165
- "no_repeat_ngram_size": 0,
166
- "encoder_no_repeat_ngram_size": 0,
167
- "bad_words_ids": null,
168
- "num_return_sequences": 1,
169
- "output_scores": false,
170
- "return_dict_in_generate": false,
171
- "forced_bos_token_id": null,
172
- "forced_eos_token_id": null,
173
- "remove_invalid_values": false,
174
- "exponential_decay_length_penalty": null,
175
- "suppress_tokens": null,
176
- "begin_suppress_tokens": null,
177
- "num_beam_groups": 1,
178
- "diversity_penalty": 0.0,
179
- "_name_or_path": "answerdotai/ModernBERT-large",
180
- "transformers_version": "4.57.0.dev0",
181
- "cls_token_id": 50281,
182
- "gradient_checkpointing": false,
183
- "layer_norm_eps": 1e-05,
184
- "model_type": "modernbert",
185
- "position_embedding_type": "absolute",
186
- "tf_legacy_loss": false,
187
- "use_bfloat16": false,
188
- "vocab_size": 50368,
189
- "max_position_embeddings": 8192,
190
- "hidden_size": 1024,
191
- "intermediate_size": 2624,
192
- "num_hidden_layers": 28,
193
- "num_attention_heads": 16,
194
- "initializer_range": 0.02,
195
- "initializer_cutoff_factor": 2.0,
196
- "norm_eps": 1e-05,
197
- "norm_bias": false,
198
- "global_rope_theta": 160000.0,
199
- "attention_bias": false,
200
- "attention_dropout": 0.0,
201
- "hidden_activation": "gelu",
202
- "global_attn_every_n_layers": 3,
203
- "local_attention": 128,
204
- "local_rope_theta": 10000.0,
205
- "embedding_dropout": 0.0,
206
- "mlp_bias": false,
207
- "mlp_dropout": 0.0,
208
- "decoder_bias": true,
209
- "classifier_pooling": "mean",
210
- "classifier_dropout": 0.0,
211
- "classifier_bias": false,
212
- "classifier_activation": "gelu",
213
- "deterministic_flash_attn": false,
214
- "sparse_prediction": false,
215
- "sparse_pred_ignore_index": -100,
216
- "repad_logits_with_grad": false,
217
- "output_attentions": false
218
- },
219
- "output_dim": 1024,
220
- "nth_text_layer": 22
221
  }
 
1
  {
2
+ "model_type": "pe_audio_frame",
3
+ "audio_config": {
4
+ "hidden_size": 1024,
5
+ "intermediate_size": 2752,
6
+ "num_hidden_layers": 16,
7
+ "num_attention_heads": 8,
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:a61998eac35acef13686e3438f4ada1f92ff6bc5d081f50756ffcc73f2524ff8
3
- size 2537855336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75714378f70454aa407ab78a164360e65552d61d2b86098a9b96dcd514f2d45
3
+ size 2243146240
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",