Safetensors
Jayjay55 commited on
Commit
b8c8adc
·
verified ·
1 Parent(s): 1c78f5c

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ FireRedAudio/tokenizer.json filter=lfs diff=lfs merge=lfs -text
FireRedAudio/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FireRedAudioForCausalLM"
4
+ ],
5
+ "audio_encoder_config": {
6
+ "_attn_implementation_autoset": true,
7
+ "activation_dropout": 0.1,
8
+ "activation_function": "gelu",
9
+ "add_cross_attention": false,
10
+ "architectures": [
11
+ "FireRed_AudioEncoder"
12
+ ],
13
+ "attention_dropout": 0.1,
14
+ "bos_token_id": null,
15
+ "cross_attention_hidden_size": null,
16
+ "d_model": 1280,
17
+ "decoder_start_token_id": null,
18
+ "dropout": 0.1,
19
+ "dtype": "bfloat16",
20
+ "encoder_attention_heads": 20,
21
+ "encoder_ffn_dim": 5120,
22
+ "encoder_layers": 32,
23
+ "eos_token_id": null,
24
+ "finetuning_task": null,
25
+ "init_std": 0.02,
26
+ "initializer_range": 0.02,
27
+ "is_decoder": false,
28
+ "max_source_positions": 1500,
29
+ "model_type": "firered_audio_encoder",
30
+ "n_window": 1500,
31
+ "num_mel_bins": 128,
32
+ "output_dim": 4096,
33
+ "pad_token_id": null,
34
+ "prefix": null,
35
+ "pruned_heads": {},
36
+ "scale_embedding": false,
37
+ "sep_token_id": null,
38
+ "task_specific_params": null,
39
+ "tf_legacy_loss": false,
40
+ "tie_encoder_decoder": false,
41
+ "tie_word_embeddings": true,
42
+ "tokenizer_class": null,
43
+ "torchscript": false,
44
+ "use_bfloat16": false
45
+ },
46
+ "audio_special_no_latent_id": 248092,
47
+ "audio_special_token": "<|AUDIO|>",
48
+ "audio_special_token_id": 248091,
49
+ "audio_special_token_no_latent": "<|AUDIO_NO_LATENT|>",
50
+ "backbone_config": {
51
+ "attention_bias": false,
52
+ "attention_dropout": 0.1,
53
+ "attn_output_gate": true,
54
+ "bos_token_id": null,
55
+ "dtype": "bfloat16",
56
+ "eos_token_id": 248044,
57
+ "full_attention_interval": 4,
58
+ "head_dim": 256,
59
+ "hidden_act": "silu",
60
+ "hidden_size": 4096,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 12288,
63
+ "layer_types": [
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "full_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "full_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "full_attention",
92
+ "linear_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "full_attention"
96
+ ],
97
+ "linear_conv_kernel_dim": 4,
98
+ "linear_key_head_dim": 128,
99
+ "linear_num_key_heads": 16,
100
+ "linear_num_value_heads": 32,
101
+ "linear_value_head_dim": 128,
102
+ "mamba_ssm_dtype": "float32",
103
+ "max_position_embeddings": 262144,
104
+ "mlp_only_layers": [],
105
+ "model_type": "qwen3_5_text",
106
+ "mtp_num_hidden_layers": 1,
107
+ "mtp_use_dedicated_embeddings": false,
108
+ "num_attention_heads": 16,
109
+ "num_hidden_layers": 32,
110
+ "num_key_value_heads": 4,
111
+ "pad_token_id": null,
112
+ "partial_rotary_factor": 0.25,
113
+ "rms_norm_eps": 1e-06,
114
+ "rope_parameters": {
115
+ "mrope_interleaved": true,
116
+ "mrope_section": [
117
+ 11,
118
+ 11,
119
+ 10
120
+ ],
121
+ "partial_rotary_factor": 0.25,
122
+ "rope_theta": 10000000,
123
+ "rope_type": "default"
124
+ },
125
+ "tie_word_embeddings": false,
126
+ "use_cache": true,
127
+ "vocab_size": 248320
128
+ },
129
+ "dit_config": {
130
+ "backbone_hidden_size": 4096,
131
+ "depth": 11,
132
+ "hidden_size": 1024,
133
+ "history_patches": 2,
134
+ "mlp_ratio": 4.0,
135
+ "model_type": "red_dit",
136
+ "num_heads": 16,
137
+ "patch_size": 4,
138
+ "train_cfg_rate": 0.1,
139
+ "vae_channels": 64
140
+ },
141
+ "dtype": "bfloat16",
142
+ "eosp_idx": 248078,
143
+ "model_type": "firered_audio",
144
+ "patch_encoder_config": {
145
+ "depth": 8,
146
+ "hidden_size": 1024,
147
+ "mlp_ratio": 4,
148
+ "model_type": "red_patch_encoder",
149
+ "num_heads": 16,
150
+ "out_dim": 4096,
151
+ "patch_size": 4,
152
+ "semantic_dim": 0,
153
+ "vae_dim": 64
154
+ },
155
+ "red_vae_config": {
156
+ "audio_patch_size": 480,
157
+ "audio_sample_rate": 24000,
158
+ "downsample_num_hidden_layers": 4,
159
+ "extra_downsample_rate": 2,
160
+ "hidden_size": 896,
161
+ "initializer_range": 0.02,
162
+ "intermediate_size": 3584,
163
+ "max_position_embeddings": 32768,
164
+ "max_window_layers": 0,
165
+ "model_type": "red_vae_audio_encoder_v1",
166
+ "num_attention_heads": 14,
167
+ "num_hidden_layers": 18,
168
+ "num_key_value_heads": 2,
169
+ "out_dim": 64,
170
+ "sliding_window": 64,
171
+ "use_sliding_window": true
172
+ },
173
+ "sosp_idx": 248077,
174
+ "transformers_version": "5.8.0"
175
+ }
FireRedAudio/model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15d9fc56c013769ed761c6a7a03ffe0d8a098aea95b4fa09b903ceb41ba4256
3
+ size 3368115912
FireRedAudio/model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486f1f1d3c80cfc733084c95842605aec007a97bc5a43e48a593552861e6c418
3
+ size 4973912528
FireRedAudio/model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed08598bb7040daa33f3f9f91c8d899eee01a94406d02aa7ae748b0f0e50706f
3
+ size 4988367272
FireRedAudio/model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d476dc2024bf8a724fd46ec974ca8dd24db80b4e2142eda53f0c50549adc83
3
+ size 4954204904
FireRedAudio/model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443c158f6573595eeb3e6be53976445f1f4fcd3a538463faa22efc871029b4b4
3
+ size 2942690408
FireRedAudio/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
FireRedAudio/processor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 300,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 128,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 4800000,
10
+ "nb_max_frames": 30000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": true,
14
+ "sampling_rate": 16000
15
+ },
16
+ "processor_class": "FireRedAudioProcessor"
17
+ }
FireRedAudio/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858cf32246e699cef49c00afe947043f2ad1660dbe0484732912c74365d21069
3
+ size 19993078
FireRedAudio/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "chat_template": null,
9
+ "clean_up_tokenization_spaces": false,
10
+ "eos_token": "<|im_end|>",
11
+ "errors": "replace",
12
+ "image_token": "<|image_pad|>",
13
+ "is_local": true,
14
+ "local_files_only": false,
15
+ "model_max_length": 262144,
16
+ "model_specific_special_tokens": {
17
+ "audio_bos_token": "<|audio_start|>",
18
+ "audio_eos_token": "<|audio_end|>",
19
+ "audio_token": "<|audio_pad|>",
20
+ "image_token": "<|image_pad|>",
21
+ "video_token": "<|video_pad|>",
22
+ "vision_bos_token": "<|vision_start|>",
23
+ "vision_eos_token": "<|vision_end|>"
24
+ },
25
+ "pad_token": "<|endoftext|>",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }
RedAE_decoder/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020b4d5eb7bcf3dbca1133023f6a62366cc213491bbb5f334b8691e2949e0152
3
+ size 8402858166