Hugging Face's logo

kmhf
/
hf-moshika

Text2Text Generation
Transformers
Safetensors
Moshi
Inference Endpoints
Model card Files Community
ylacombe HF staff commited on
Commit
a7dcb3c
•
1 Parent(s): d0deb41

Upload MoshiForConditionalGeneration

Browse files
Files changed (7) hide show
  1. config.json +142 -0
  2. generation_config.json +18 -0
  3. model-00001-of-00004.safetensors +3 -0
  4. model-00002-of-00004.safetensors +3 -0
  5. model-00003-of-00004.safetensors +3 -0
  6. model-00004-of-00004.safetensors +3 -0
  7. model.safetensors.index.json +690 -0
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MoshiForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "audio_encoder": {
7
+ "_name_or_path": "kyutai/mimi",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "MimiModel"
11
+ ],
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "audio_channels": 1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "codebook_dim": 256,
20
+ "codebook_size": 2048,
21
+ "compress": 2,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "dilation_growth_rate": 2,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": null,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "frame_rate": 12.5,
35
+ "head_dim": 64,
36
+ "hidden_act": "gelu",
37
+ "hidden_size": 512,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 2048,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "kernel_size": 7,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "last_kernel_size": 3,
52
+ "layer_scale_initial_scale": 0.01,
53
+ "length_penalty": 1.0,
54
+ "max_length": 20,
55
+ "max_position_embeddings": 8000,
56
+ "min_length": 0,
57
+ "model_type": "mimi",
58
+ "no_repeat_ngram_size": 0,
59
+ "norm_eps": 1e-05,
60
+ "normalize": false,
61
+ "num_attention_heads": 8,
62
+ "num_beam_groups": 1,
63
+ "num_beams": 1,
64
+ "num_filters": 64,
65
+ "num_hidden_layers": 8,
66
+ "num_key_value_heads": 8,
67
+ "num_quantizers": 32,
68
+ "num_residual_layers": 1,
69
+ "num_return_sequences": 1,
70
+ "num_semantic_quantizers": 1,
71
+ "output_attentions": false,
72
+ "output_hidden_states": false,
73
+ "output_scores": false,
74
+ "pad_mode": "constant",
75
+ "pad_token_id": null,
76
+ "prefix": null,
77
+ "problem_type": null,
78
+ "pruned_heads": {},
79
+ "remove_invalid_values": false,
80
+ "repetition_penalty": 1.0,
81
+ "residual_kernel_size": 3,
82
+ "return_dict": true,
83
+ "return_dict_in_generate": false,
84
+ "rope_theta": 10000.0,
85
+ "sampling_rate": 24000,
86
+ "sep_token_id": null,
87
+ "sliding_window": 250,
88
+ "suppress_tokens": null,
89
+ "task_specific_params": null,
90
+ "temperature": 1.0,
91
+ "tf_legacy_loss": false,
92
+ "tie_encoder_decoder": false,
93
+ "tie_word_embeddings": true,
94
+ "tokenizer_class": null,
95
+ "top_k": 50,
96
+ "top_p": 1.0,
97
+ "torch_dtype": "float32",
98
+ "torchscript": false,
99
+ "trim_right_ratio": 1.0,
100
+ "typical_p": 1.0,
101
+ "upsample_groups": 512,
102
+ "upsampling_ratios": [
103
+ 8,
104
+ 6,
105
+ 5,
106
+ 4
107
+ ],
108
+ "use_bfloat16": false,
109
+ "use_cache": false,
110
+ "use_causal_conv": true,
111
+ "use_conv_shortcut": false,
112
+ "vector_quantization_hidden_dimension": 256
113
+ },
114
+ "audio_vocab_size": 2048,
115
+ "depth_ffn_dim": 5632,
116
+ "depth_head_dim": 64,
117
+ "depth_hidden_size": 1024,
118
+ "depth_max_position_embeddings": 9,
119
+ "depth_num_attention_heads": 16,
120
+ "depth_num_hidden_layers": 6,
121
+ "depth_num_key_value_heads": 16,
122
+ "depth_sliding_window": 8,
123
+ "ffn_dim": 22528,
124
+ "head_dim": 128,
125
+ "hidden_act": "silu",
126
+ "hidden_size": 4096,
127
+ "initializer_range": 0.02,
128
+ "max_position_embeddings": 3000,
129
+ "model_type": "moshi",
130
+ "num_attention_heads": 32,
131
+ "num_codebooks": 8,
132
+ "num_hidden_layers": 32,
133
+ "num_key_value_heads": 32,
134
+ "rms_norm_eps": 1e-08,
135
+ "rope_theta": 10000.0,
136
+ "sliding_window": 3000,
137
+ "tie_word_embeddings": false,
138
+ "torch_dtype": "bfloat16",
139
+ "transformers_version": "4.46.0.dev0",
140
+ "use_cache": true,
141
+ "vocab_size": 32000
142
+ }
generation_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 32000,
3
+ "cache_implementation": "sliding_window",
4
+ "depth_decoder_config": {
5
+ "cache_implementation": "sliding_window",
6
+ "do_sample": true,
7
+ "max_length": 9,
8
+ "min_length": 9,
9
+ "temperature": 0.8,
10
+ "top_k": 250,
11
+ "transformers_version": "4.46.0.dev0"
12
+ },
13
+ "do_sample": true,
14
+ "pad_token_id": 32000,
15
+ "temp": 0.7,
16
+ "top_k": 25,
17
+ "transformers_version": "4.46.0.dev0"
18
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb79752c108da9c4b6ed8be4049ae62468e2b45a787a07a8e3961d45ec9c9f7
3
+ size 4967882658
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73314c175e61c8b6d0b3c249748696cf0ce681d1d925ba0991eead019b9a86a3
3
+ size 4932710304
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc67b1a408a2e4aef6bfc8983ae96efff76c927f421cd33d3eb410d57719d97
3
+ size 4970984712
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4009ae4307acfdf6e5ef21c67b210229bb0e095617d6e945d559b91963e60750
3
+ size 696274344
model.safetensors.index.json ADDED
@@ -0,0 +1,690 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15567761090
4
+ },
5
+ "weight_map": {
6
+ "audio_encoder.decoder.layers.0.conv.bias": "model-00001-of-00004.safetensors",
7
+ "audio_encoder.decoder.layers.0.conv.weight": "model-00001-of-00004.safetensors",
8
+ "audio_encoder.decoder.layers.11.conv.bias": "model-00001-of-00004.safetensors",
9
+ "audio_encoder.decoder.layers.11.conv.weight": "model-00001-of-00004.safetensors",
10
+ "audio_encoder.decoder.layers.12.block.1.conv.bias": "model-00001-of-00004.safetensors",
11
+ "audio_encoder.decoder.layers.12.block.1.conv.weight": "model-00001-of-00004.safetensors",
12
+ "audio_encoder.decoder.layers.12.block.3.conv.bias": "model-00001-of-00004.safetensors",
13
+ "audio_encoder.decoder.layers.12.block.3.conv.weight": "model-00001-of-00004.safetensors",
14
+ "audio_encoder.decoder.layers.14.conv.bias": "model-00001-of-00004.safetensors",
15
+ "audio_encoder.decoder.layers.14.conv.weight": "model-00001-of-00004.safetensors",
16
+ "audio_encoder.decoder.layers.2.conv.bias": "model-00001-of-00004.safetensors",
17
+ "audio_encoder.decoder.layers.2.conv.weight": "model-00001-of-00004.safetensors",
18
+ "audio_encoder.decoder.layers.3.block.1.conv.bias": "model-00001-of-00004.safetensors",
19
+ "audio_encoder.decoder.layers.3.block.1.conv.weight": "model-00001-of-00004.safetensors",
20
+ "audio_encoder.decoder.layers.3.block.3.conv.bias": "model-00001-of-00004.safetensors",
21
+ "audio_encoder.decoder.layers.3.block.3.conv.weight": "model-00001-of-00004.safetensors",
22
+ "audio_encoder.decoder.layers.5.conv.bias": "model-00001-of-00004.safetensors",
23
+ "audio_encoder.decoder.layers.5.conv.weight": "model-00001-of-00004.safetensors",
24
+ "audio_encoder.decoder.layers.6.block.1.conv.bias": "model-00001-of-00004.safetensors",
25
+ "audio_encoder.decoder.layers.6.block.1.conv.weight": "model-00001-of-00004.safetensors",
26
+ "audio_encoder.decoder.layers.6.block.3.conv.bias": "model-00001-of-00004.safetensors",
27
+ "audio_encoder.decoder.layers.6.block.3.conv.weight": "model-00001-of-00004.safetensors",
28
+ "audio_encoder.decoder.layers.8.conv.bias": "model-00001-of-00004.safetensors",
29
+ "audio_encoder.decoder.layers.8.conv.weight": "model-00001-of-00004.safetensors",
30
+ "audio_encoder.decoder.layers.9.block.1.conv.bias": "model-00001-of-00004.safetensors",
31
+ "audio_encoder.decoder.layers.9.block.1.conv.weight": "model-00001-of-00004.safetensors",
32
+ "audio_encoder.decoder.layers.9.block.3.conv.bias": "model-00001-of-00004.safetensors",
33
+ "audio_encoder.decoder.layers.9.block.3.conv.weight": "model-00001-of-00004.safetensors",
34
+ "audio_encoder.decoder_transformer.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
35
+ "audio_encoder.decoder_transformer.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
36
+ "audio_encoder.decoder_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
37
+ "audio_encoder.decoder_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
38
+ "audio_encoder.decoder_transformer.layers.0.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
39
+ "audio_encoder.decoder_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
40
+ "audio_encoder.decoder_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
41
+ "audio_encoder.decoder_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
42
+ "audio_encoder.decoder_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
43
+ "audio_encoder.decoder_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
44
+ "audio_encoder.decoder_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
45
+ "audio_encoder.decoder_transformer.layers.0.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
46
+ "audio_encoder.decoder_transformer.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
47
+ "audio_encoder.decoder_transformer.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
48
+ "audio_encoder.decoder_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
49
+ "audio_encoder.decoder_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
50
+ "audio_encoder.decoder_transformer.layers.1.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
51
+ "audio_encoder.decoder_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
52
+ "audio_encoder.decoder_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
53
+ "audio_encoder.decoder_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
54
+ "audio_encoder.decoder_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
55
+ "audio_encoder.decoder_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
56
+ "audio_encoder.decoder_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
57
+ "audio_encoder.decoder_transformer.layers.1.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
58
+ "audio_encoder.decoder_transformer.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
59
+ "audio_encoder.decoder_transformer.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
60
+ "audio_encoder.decoder_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
61
+ "audio_encoder.decoder_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
62
+ "audio_encoder.decoder_transformer.layers.2.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
63
+ "audio_encoder.decoder_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
64
+ "audio_encoder.decoder_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
65
+ "audio_encoder.decoder_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
66
+ "audio_encoder.decoder_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
67
+ "audio_encoder.decoder_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
68
+ "audio_encoder.decoder_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
69
+ "audio_encoder.decoder_transformer.layers.2.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
70
+ "audio_encoder.decoder_transformer.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
71
+ "audio_encoder.decoder_transformer.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
72
+ "audio_encoder.decoder_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
73
+ "audio_encoder.decoder_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
74
+ "audio_encoder.decoder_transformer.layers.3.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
75
+ "audio_encoder.decoder_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
76
+ "audio_encoder.decoder_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
77
+ "audio_encoder.decoder_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
78
+ "audio_encoder.decoder_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
79
+ "audio_encoder.decoder_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
80
+ "audio_encoder.decoder_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
81
+ "audio_encoder.decoder_transformer.layers.3.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
82
+ "audio_encoder.decoder_transformer.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
83
+ "audio_encoder.decoder_transformer.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
84
+ "audio_encoder.decoder_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
85
+ "audio_encoder.decoder_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
86
+ "audio_encoder.decoder_transformer.layers.4.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
87
+ "audio_encoder.decoder_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
88
+ "audio_encoder.decoder_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
89
+ "audio_encoder.decoder_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
90
+ "audio_encoder.decoder_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
91
+ "audio_encoder.decoder_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
92
+ "audio_encoder.decoder_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
93
+ "audio_encoder.decoder_transformer.layers.4.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
94
+ "audio_encoder.decoder_transformer.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
95
+ "audio_encoder.decoder_transformer.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
96
+ "audio_encoder.decoder_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
97
+ "audio_encoder.decoder_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
98
+ "audio_encoder.decoder_transformer.layers.5.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
99
+ "audio_encoder.decoder_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
100
+ "audio_encoder.decoder_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
101
+ "audio_encoder.decoder_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
102
+ "audio_encoder.decoder_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
103
+ "audio_encoder.decoder_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
104
+ "audio_encoder.decoder_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
105
+ "audio_encoder.decoder_transformer.layers.5.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
106
+ "audio_encoder.decoder_transformer.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
107
+ "audio_encoder.decoder_transformer.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
108
+ "audio_encoder.decoder_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
109
+ "audio_encoder.decoder_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
110
+ "audio_encoder.decoder_transformer.layers.6.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
111
+ "audio_encoder.decoder_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
112
+ "audio_encoder.decoder_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
113
+ "audio_encoder.decoder_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
114
+ "audio_encoder.decoder_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
115
+ "audio_encoder.decoder_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
116
+ "audio_encoder.decoder_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
117
+ "audio_encoder.decoder_transformer.layers.6.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
118
+ "audio_encoder.decoder_transformer.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
119
+ "audio_encoder.decoder_transformer.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "audio_encoder.decoder_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
121
+ "audio_encoder.decoder_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
122
+ "audio_encoder.decoder_transformer.layers.7.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
123
+ "audio_encoder.decoder_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
124
+ "audio_encoder.decoder_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
125
+ "audio_encoder.decoder_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
126
+ "audio_encoder.decoder_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
127
+ "audio_encoder.decoder_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
128
+ "audio_encoder.decoder_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
129
+ "audio_encoder.decoder_transformer.layers.7.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
130
+ "audio_encoder.downsample.conv.weight": "model-00001-of-00004.safetensors",
131
+ "audio_encoder.encoder.layers.0.conv.bias": "model-00001-of-00004.safetensors",
132
+ "audio_encoder.encoder.layers.0.conv.weight": "model-00001-of-00004.safetensors",
133
+ "audio_encoder.encoder.layers.1.block.1.conv.bias": "model-00001-of-00004.safetensors",
134
+ "audio_encoder.encoder.layers.1.block.1.conv.weight": "model-00001-of-00004.safetensors",
135
+ "audio_encoder.encoder.layers.1.block.3.conv.bias": "model-00001-of-00004.safetensors",
136
+ "audio_encoder.encoder.layers.1.block.3.conv.weight": "model-00001-of-00004.safetensors",
137
+ "audio_encoder.encoder.layers.10.block.1.conv.bias": "model-00001-of-00004.safetensors",
138
+ "audio_encoder.encoder.layers.10.block.1.conv.weight": "model-00001-of-00004.safetensors",
139
+ "audio_encoder.encoder.layers.10.block.3.conv.bias": "model-00001-of-00004.safetensors",
140
+ "audio_encoder.encoder.layers.10.block.3.conv.weight": "model-00001-of-00004.safetensors",
141
+ "audio_encoder.encoder.layers.12.conv.bias": "model-00001-of-00004.safetensors",
142
+ "audio_encoder.encoder.layers.12.conv.weight": "model-00001-of-00004.safetensors",
143
+ "audio_encoder.encoder.layers.14.conv.bias": "model-00001-of-00004.safetensors",
144
+ "audio_encoder.encoder.layers.14.conv.weight": "model-00001-of-00004.safetensors",
145
+ "audio_encoder.encoder.layers.3.conv.bias": "model-00001-of-00004.safetensors",
146
+ "audio_encoder.encoder.layers.3.conv.weight": "model-00001-of-00004.safetensors",
147
+ "audio_encoder.encoder.layers.4.block.1.conv.bias": "model-00001-of-00004.safetensors",
148
+ "audio_encoder.encoder.layers.4.block.1.conv.weight": "model-00001-of-00004.safetensors",
149
+ "audio_encoder.encoder.layers.4.block.3.conv.bias": "model-00001-of-00004.safetensors",
150
+ "audio_encoder.encoder.layers.4.block.3.conv.weight": "model-00001-of-00004.safetensors",
151
+ "audio_encoder.encoder.layers.6.conv.bias": "model-00001-of-00004.safetensors",
152
+ "audio_encoder.encoder.layers.6.conv.weight": "model-00001-of-00004.safetensors",
153
+ "audio_encoder.encoder.layers.7.block.1.conv.bias": "model-00001-of-00004.safetensors",
154
+ "audio_encoder.encoder.layers.7.block.1.conv.weight": "model-00001-of-00004.safetensors",
155
+ "audio_encoder.encoder.layers.7.block.3.conv.bias": "model-00001-of-00004.safetensors",
156
+ "audio_encoder.encoder.layers.7.block.3.conv.weight": "model-00001-of-00004.safetensors",
157
+ "audio_encoder.encoder.layers.9.conv.bias": "model-00001-of-00004.safetensors",
158
+ "audio_encoder.encoder.layers.9.conv.weight": "model-00001-of-00004.safetensors",
159
+ "audio_encoder.encoder_transformer.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
160
+ "audio_encoder.encoder_transformer.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
161
+ "audio_encoder.encoder_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
162
+ "audio_encoder.encoder_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
163
+ "audio_encoder.encoder_transformer.layers.0.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
164
+ "audio_encoder.encoder_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
165
+ "audio_encoder.encoder_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
166
+ "audio_encoder.encoder_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
167
+ "audio_encoder.encoder_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
168
+ "audio_encoder.encoder_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
169
+ "audio_encoder.encoder_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
170
+ "audio_encoder.encoder_transformer.layers.0.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
171
+ "audio_encoder.encoder_transformer.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
172
+ "audio_encoder.encoder_transformer.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
173
+ "audio_encoder.encoder_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
174
+ "audio_encoder.encoder_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
175
+ "audio_encoder.encoder_transformer.layers.1.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
176
+ "audio_encoder.encoder_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
177
+ "audio_encoder.encoder_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
178
+ "audio_encoder.encoder_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
179
+ "audio_encoder.encoder_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
180
+ "audio_encoder.encoder_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
181
+ "audio_encoder.encoder_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
182
+ "audio_encoder.encoder_transformer.layers.1.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
183
+ "audio_encoder.encoder_transformer.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
184
+ "audio_encoder.encoder_transformer.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
185
+ "audio_encoder.encoder_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
186
+ "audio_encoder.encoder_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
187
+ "audio_encoder.encoder_transformer.layers.2.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
188
+ "audio_encoder.encoder_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
189
+ "audio_encoder.encoder_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
190
+ "audio_encoder.encoder_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
191
+ "audio_encoder.encoder_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
192
+ "audio_encoder.encoder_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
193
+ "audio_encoder.encoder_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
194
+ "audio_encoder.encoder_transformer.layers.2.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
195
+ "audio_encoder.encoder_transformer.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
196
+ "audio_encoder.encoder_transformer.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
197
+ "audio_encoder.encoder_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
198
+ "audio_encoder.encoder_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
199
+ "audio_encoder.encoder_transformer.layers.3.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
200
+ "audio_encoder.encoder_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
201
+ "audio_encoder.encoder_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
202
+ "audio_encoder.encoder_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
203
+ "audio_encoder.encoder_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
204
+ "audio_encoder.encoder_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
205
+ "audio_encoder.encoder_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
206
+ "audio_encoder.encoder_transformer.layers.3.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
207
+ "audio_encoder.encoder_transformer.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
208
+ "audio_encoder.encoder_transformer.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
209
+ "audio_encoder.encoder_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
210
+ "audio_encoder.encoder_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
211
+ "audio_encoder.encoder_transformer.layers.4.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
212
+ "audio_encoder.encoder_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
213
+ "audio_encoder.encoder_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
214
+ "audio_encoder.encoder_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
215
+ "audio_encoder.encoder_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
216
+ "audio_encoder.encoder_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
217
+ "audio_encoder.encoder_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
218
+ "audio_encoder.encoder_transformer.layers.4.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
219
+ "audio_encoder.encoder_transformer.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
220
+ "audio_encoder.encoder_transformer.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "audio_encoder.encoder_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
222
+ "audio_encoder.encoder_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
223
+ "audio_encoder.encoder_transformer.layers.5.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
224
+ "audio_encoder.encoder_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
225
+ "audio_encoder.encoder_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
226
+ "audio_encoder.encoder_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
227
+ "audio_encoder.encoder_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
228
+ "audio_encoder.encoder_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
229
+ "audio_encoder.encoder_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
230
+ "audio_encoder.encoder_transformer.layers.5.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
231
+ "audio_encoder.encoder_transformer.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
232
+ "audio_encoder.encoder_transformer.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
233
+ "audio_encoder.encoder_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
234
+ "audio_encoder.encoder_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
235
+ "audio_encoder.encoder_transformer.layers.6.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
236
+ "audio_encoder.encoder_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
237
+ "audio_encoder.encoder_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
238
+ "audio_encoder.encoder_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
239
+ "audio_encoder.encoder_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
240
+ "audio_encoder.encoder_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
241
+ "audio_encoder.encoder_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
242
+ "audio_encoder.encoder_transformer.layers.6.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
243
+ "audio_encoder.encoder_transformer.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
244
+ "audio_encoder.encoder_transformer.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
245
+ "audio_encoder.encoder_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
246
+ "audio_encoder.encoder_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
247
+ "audio_encoder.encoder_transformer.layers.7.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
248
+ "audio_encoder.encoder_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
249
+ "audio_encoder.encoder_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
250
+ "audio_encoder.encoder_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
251
+ "audio_encoder.encoder_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
252
+ "audio_encoder.encoder_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
253
+ "audio_encoder.encoder_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
254
+ "audio_encoder.encoder_transformer.layers.7.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
255
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.input_proj.weight": "model-00001-of-00004.safetensors",
256
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.cluster_usage": "model-00001-of-00004.safetensors",
257
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.embed_sum": "model-00001-of-00004.safetensors",
258
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.initialized": "model-00001-of-00004.safetensors",
259
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.cluster_usage": "model-00001-of-00004.safetensors",
260
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.embed_sum": "model-00001-of-00004.safetensors",
261
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.initialized": "model-00001-of-00004.safetensors",
262
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.cluster_usage": "model-00001-of-00004.safetensors",
263
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.embed_sum": "model-00001-of-00004.safetensors",
264
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.initialized": "model-00001-of-00004.safetensors",
265
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.cluster_usage": "model-00001-of-00004.safetensors",
266
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.embed_sum": "model-00001-of-00004.safetensors",
267
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.initialized": "model-00001-of-00004.safetensors",
268
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.cluster_usage": "model-00001-of-00004.safetensors",
269
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.embed_sum": "model-00001-of-00004.safetensors",
270
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.initialized": "model-00001-of-00004.safetensors",
271
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.cluster_usage": "model-00001-of-00004.safetensors",
272
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.embed_sum": "model-00001-of-00004.safetensors",
273
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.initialized": "model-00001-of-00004.safetensors",
274
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.cluster_usage": "model-00001-of-00004.safetensors",
275
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.embed_sum": "model-00001-of-00004.safetensors",
276
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.initialized": "model-00001-of-00004.safetensors",
277
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.cluster_usage": "model-00001-of-00004.safetensors",
278
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.embed_sum": "model-00001-of-00004.safetensors",
279
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.initialized": "model-00001-of-00004.safetensors",
280
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.cluster_usage": "model-00001-of-00004.safetensors",
281
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.embed_sum": "model-00001-of-00004.safetensors",
282
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.initialized": "model-00001-of-00004.safetensors",
283
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.cluster_usage": "model-00001-of-00004.safetensors",
284
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.embed_sum": "model-00001-of-00004.safetensors",
285
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.initialized": "model-00001-of-00004.safetensors",
286
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.cluster_usage": "model-00001-of-00004.safetensors",
287
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.embed_sum": "model-00001-of-00004.safetensors",
288
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.initialized": "model-00001-of-00004.safetensors",
289
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.cluster_usage": "model-00001-of-00004.safetensors",
290
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.embed_sum": "model-00001-of-00004.safetensors",
291
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.initialized": "model-00001-of-00004.safetensors",
292
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.cluster_usage": "model-00001-of-00004.safetensors",
293
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.embed_sum": "model-00001-of-00004.safetensors",
294
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.initialized": "model-00001-of-00004.safetensors",
295
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.cluster_usage": "model-00001-of-00004.safetensors",
296
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.embed_sum": "model-00001-of-00004.safetensors",
297
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.initialized": "model-00001-of-00004.safetensors",
298
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.cluster_usage": "model-00001-of-00004.safetensors",
299
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.embed_sum": "model-00001-of-00004.safetensors",
300
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.initialized": "model-00001-of-00004.safetensors",
301
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.cluster_usage": "model-00001-of-00004.safetensors",
302
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.embed_sum": "model-00001-of-00004.safetensors",
303
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.initialized": "model-00001-of-00004.safetensors",
304
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.cluster_usage": "model-00001-of-00004.safetensors",
305
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.embed_sum": "model-00001-of-00004.safetensors",
306
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.initialized": "model-00001-of-00004.safetensors",
307
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.cluster_usage": "model-00001-of-00004.safetensors",
308
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.embed_sum": "model-00001-of-00004.safetensors",
309
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.initialized": "model-00001-of-00004.safetensors",
310
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.cluster_usage": "model-00001-of-00004.safetensors",
311
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.embed_sum": "model-00001-of-00004.safetensors",
312
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.initialized": "model-00001-of-00004.safetensors",
313
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.cluster_usage": "model-00001-of-00004.safetensors",
314
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.embed_sum": "model-00001-of-00004.safetensors",
315
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.initialized": "model-00001-of-00004.safetensors",
316
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.cluster_usage": "model-00001-of-00004.safetensors",
317
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.embed_sum": "model-00001-of-00004.safetensors",
318
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.initialized": "model-00001-of-00004.safetensors",
319
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.cluster_usage": "model-00001-of-00004.safetensors",
320
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.embed_sum": "model-00001-of-00004.safetensors",
321
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.initialized": "model-00001-of-00004.safetensors",
322
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.cluster_usage": "model-00001-of-00004.safetensors",
323
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.embed_sum": "model-00001-of-00004.safetensors",
324
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.initialized": "model-00001-of-00004.safetensors",
325
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.cluster_usage": "model-00001-of-00004.safetensors",
326
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.embed_sum": "model-00001-of-00004.safetensors",
327
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.initialized": "model-00001-of-00004.safetensors",
328
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.cluster_usage": "model-00001-of-00004.safetensors",
329
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.embed_sum": "model-00001-of-00004.safetensors",
330
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.initialized": "model-00001-of-00004.safetensors",
331
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.cluster_usage": "model-00001-of-00004.safetensors",
332
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.embed_sum": "model-00001-of-00004.safetensors",
333
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.initialized": "model-00001-of-00004.safetensors",
334
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.cluster_usage": "model-00001-of-00004.safetensors",
335
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.embed_sum": "model-00001-of-00004.safetensors",
336
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.initialized": "model-00001-of-00004.safetensors",
337
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.cluster_usage": "model-00001-of-00004.safetensors",
338
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.embed_sum": "model-00001-of-00004.safetensors",
339
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.initialized": "model-00001-of-00004.safetensors",
340
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.cluster_usage": "model-00001-of-00004.safetensors",
341
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.embed_sum": "model-00001-of-00004.safetensors",
342
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.initialized": "model-00001-of-00004.safetensors",
343
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.cluster_usage": "model-00001-of-00004.safetensors",
344
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.embed_sum": "model-00001-of-00004.safetensors",
345
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.initialized": "model-00001-of-00004.safetensors",
346
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.cluster_usage": "model-00001-of-00004.safetensors",
347
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.embed_sum": "model-00001-of-00004.safetensors",
348
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.initialized": "model-00001-of-00004.safetensors",
349
+ "audio_encoder.quantizer.acoustic_residual_vector_quantizer.output_proj.weight": "model-00001-of-00004.safetensors",
350
+ "audio_encoder.quantizer.semantic_residual_vector_quantizer.input_proj.weight": "model-00001-of-00004.safetensors",
351
+ "audio_encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.cluster_usage": "model-00001-of-00004.safetensors",
352
+ "audio_encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.embed_sum": "model-00001-of-00004.safetensors",
353
+ "audio_encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.initialized": "model-00001-of-00004.safetensors",
354
+ "audio_encoder.quantizer.semantic_residual_vector_quantizer.output_proj.weight": "model-00001-of-00004.safetensors",
355
+ "audio_encoder.upsample.conv.weight": "model-00001-of-00004.safetensors",
356
+ "decoder.lm_head.weight": "model-00003-of-00004.safetensors",
357
+ "decoder.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
358
+ "decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
359
+ "decoder.model.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
360
+ "decoder.model.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
361
+ "decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
362
+ "decoder.model.layers.0.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
363
+ "decoder.model.layers.0.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
364
+ "decoder.model.layers.0.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
365
+ "decoder.model.layers.0.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
366
+ "decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
367
+ "decoder.model.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
368
+ "decoder.model.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
369
+ "decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
370
+ "decoder.model.layers.1.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
371
+ "decoder.model.layers.1.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
372
+ "decoder.model.layers.1.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
373
+ "decoder.model.layers.1.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
374
+ "decoder.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
375
+ "decoder.model.layers.10.mlp.fc1.weight": "model-00002-of-00004.safetensors",
376
+ "decoder.model.layers.10.mlp.fc2.weight": "model-00002-of-00004.safetensors",
377
+ "decoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
378
+ "decoder.model.layers.10.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
379
+ "decoder.model.layers.10.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
380
+ "decoder.model.layers.10.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
381
+ "decoder.model.layers.10.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
382
+ "decoder.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
383
+ "decoder.model.layers.11.mlp.fc1.weight": "model-00002-of-00004.safetensors",
384
+ "decoder.model.layers.11.mlp.fc2.weight": "model-00002-of-00004.safetensors",
385
+ "decoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
386
+ "decoder.model.layers.11.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
387
+ "decoder.model.layers.11.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
388
+ "decoder.model.layers.11.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
389
+ "decoder.model.layers.11.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
390
+ "decoder.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
391
+ "decoder.model.layers.12.mlp.fc1.weight": "model-00002-of-00004.safetensors",
392
+ "decoder.model.layers.12.mlp.fc2.weight": "model-00002-of-00004.safetensors",
393
+ "decoder.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
394
+ "decoder.model.layers.12.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
395
+ "decoder.model.layers.12.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
396
+ "decoder.model.layers.12.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
397
+ "decoder.model.layers.12.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
398
+ "decoder.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "decoder.model.layers.13.mlp.fc1.weight": "model-00002-of-00004.safetensors",
400
+ "decoder.model.layers.13.mlp.fc2.weight": "model-00002-of-00004.safetensors",
401
+ "decoder.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
402
+ "decoder.model.layers.13.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
403
+ "decoder.model.layers.13.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
404
+ "decoder.model.layers.13.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
405
+ "decoder.model.layers.13.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
406
+ "decoder.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
407
+ "decoder.model.layers.14.mlp.fc1.weight": "model-00002-of-00004.safetensors",
408
+ "decoder.model.layers.14.mlp.fc2.weight": "model-00002-of-00004.safetensors",
409
+ "decoder.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
410
+ "decoder.model.layers.14.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
411
+ "decoder.model.layers.14.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
412
+ "decoder.model.layers.14.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
413
+ "decoder.model.layers.14.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
414
+ "decoder.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
415
+ "decoder.model.layers.15.mlp.fc1.weight": "model-00002-of-00004.safetensors",
416
+ "decoder.model.layers.15.mlp.fc2.weight": "model-00002-of-00004.safetensors",
417
+ "decoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
418
+ "decoder.model.layers.15.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
419
+ "decoder.model.layers.15.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
420
+ "decoder.model.layers.15.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
421
+ "decoder.model.layers.15.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
422
+ "decoder.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
423
+ "decoder.model.layers.16.mlp.fc1.weight": "model-00002-of-00004.safetensors",
424
+ "decoder.model.layers.16.mlp.fc2.weight": "model-00002-of-00004.safetensors",
425
+ "decoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
426
+ "decoder.model.layers.16.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
427
+ "decoder.model.layers.16.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
428
+ "decoder.model.layers.16.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
429
+ "decoder.model.layers.16.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
430
+ "decoder.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
431
+ "decoder.model.layers.17.mlp.fc1.weight": "model-00002-of-00004.safetensors",
432
+ "decoder.model.layers.17.mlp.fc2.weight": "model-00002-of-00004.safetensors",
433
+ "decoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
434
+ "decoder.model.layers.17.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
435
+ "decoder.model.layers.17.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
436
+ "decoder.model.layers.17.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
437
+ "decoder.model.layers.17.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
438
+ "decoder.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
439
+ "decoder.model.layers.18.mlp.fc1.weight": "model-00002-of-00004.safetensors",
440
+ "decoder.model.layers.18.mlp.fc2.weight": "model-00002-of-00004.safetensors",
441
+ "decoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
442
+ "decoder.model.layers.18.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
443
+ "decoder.model.layers.18.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
444
+ "decoder.model.layers.18.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
445
+ "decoder.model.layers.18.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
446
+ "decoder.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
447
+ "decoder.model.layers.19.mlp.fc1.weight": "model-00002-of-00004.safetensors",
448
+ "decoder.model.layers.19.mlp.fc2.weight": "model-00002-of-00004.safetensors",
449
+ "decoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
450
+ "decoder.model.layers.19.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
451
+ "decoder.model.layers.19.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
452
+ "decoder.model.layers.19.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
453
+ "decoder.model.layers.19.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
454
+ "decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
455
+ "decoder.model.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
456
+ "decoder.model.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
458
+ "decoder.model.layers.2.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
459
+ "decoder.model.layers.2.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
460
+ "decoder.model.layers.2.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
461
+ "decoder.model.layers.2.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
462
+ "decoder.model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
463
+ "decoder.model.layers.20.mlp.fc1.weight": "model-00002-of-00004.safetensors",
464
+ "decoder.model.layers.20.mlp.fc2.weight": "model-00002-of-00004.safetensors",
465
+ "decoder.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
466
+ "decoder.model.layers.20.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
467
+ "decoder.model.layers.20.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
468
+ "decoder.model.layers.20.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
469
+ "decoder.model.layers.20.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
470
+ "decoder.model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
471
+ "decoder.model.layers.21.mlp.fc1.weight": "model-00002-of-00004.safetensors",
472
+ "decoder.model.layers.21.mlp.fc2.weight": "model-00002-of-00004.safetensors",
473
+ "decoder.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
474
+ "decoder.model.layers.21.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
475
+ "decoder.model.layers.21.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
476
+ "decoder.model.layers.21.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
477
+ "decoder.model.layers.21.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
478
+ "decoder.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
479
+ "decoder.model.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
480
+ "decoder.model.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
481
+ "decoder.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
482
+ "decoder.model.layers.22.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
483
+ "decoder.model.layers.22.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
484
+ "decoder.model.layers.22.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
485
+ "decoder.model.layers.22.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
486
+ "decoder.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
487
+ "decoder.model.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
488
+ "decoder.model.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
489
+ "decoder.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
490
+ "decoder.model.layers.23.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
491
+ "decoder.model.layers.23.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
492
+ "decoder.model.layers.23.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
493
+ "decoder.model.layers.23.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
494
+ "decoder.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
495
+ "decoder.model.layers.24.mlp.fc1.weight": "model-00003-of-00004.safetensors",
496
+ "decoder.model.layers.24.mlp.fc2.weight": "model-00003-of-00004.safetensors",
497
+ "decoder.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
498
+ "decoder.model.layers.24.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
499
+ "decoder.model.layers.24.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
500
+ "decoder.model.layers.24.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
501
+ "decoder.model.layers.24.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
502
+ "decoder.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
503
+ "decoder.model.layers.25.mlp.fc1.weight": "model-00003-of-00004.safetensors",
504
+ "decoder.model.layers.25.mlp.fc2.weight": "model-00003-of-00004.safetensors",
505
+ "decoder.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
506
+ "decoder.model.layers.25.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
507
+ "decoder.model.layers.25.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
508
+ "decoder.model.layers.25.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
509
+ "decoder.model.layers.25.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
510
+ "decoder.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
511
+ "decoder.model.layers.26.mlp.fc1.weight": "model-00003-of-00004.safetensors",
512
+ "decoder.model.layers.26.mlp.fc2.weight": "model-00003-of-00004.safetensors",
513
+ "decoder.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
514
+ "decoder.model.layers.26.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
515
+ "decoder.model.layers.26.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
516
+ "decoder.model.layers.26.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
517
+ "decoder.model.layers.26.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
518
+ "decoder.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
519
+ "decoder.model.layers.27.mlp.fc1.weight": "model-00003-of-00004.safetensors",
520
+ "decoder.model.layers.27.mlp.fc2.weight": "model-00003-of-00004.safetensors",
521
+ "decoder.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
522
+ "decoder.model.layers.27.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
523
+ "decoder.model.layers.27.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
524
+ "decoder.model.layers.27.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
525
+ "decoder.model.layers.27.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
526
+ "decoder.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
527
+ "decoder.model.layers.28.mlp.fc1.weight": "model-00003-of-00004.safetensors",
528
+ "decoder.model.layers.28.mlp.fc2.weight": "model-00003-of-00004.safetensors",
529
+ "decoder.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
530
+ "decoder.model.layers.28.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
531
+ "decoder.model.layers.28.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
532
+ "decoder.model.layers.28.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
533
+ "decoder.model.layers.28.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
534
+ "decoder.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
535
+ "decoder.model.layers.29.mlp.fc1.weight": "model-00003-of-00004.safetensors",
536
+ "decoder.model.layers.29.mlp.fc2.weight": "model-00003-of-00004.safetensors",
537
+ "decoder.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
538
+ "decoder.model.layers.29.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
539
+ "decoder.model.layers.29.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
540
+ "decoder.model.layers.29.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
541
+ "decoder.model.layers.29.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
542
+ "decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
543
+ "decoder.model.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
544
+ "decoder.model.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
545
+ "decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
546
+ "decoder.model.layers.3.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
547
+ "decoder.model.layers.3.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
548
+ "decoder.model.layers.3.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
549
+ "decoder.model.layers.3.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
550
+ "decoder.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
551
+ "decoder.model.layers.30.mlp.fc1.weight": "model-00003-of-00004.safetensors",
552
+ "decoder.model.layers.30.mlp.fc2.weight": "model-00003-of-00004.safetensors",
553
+ "decoder.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
554
+ "decoder.model.layers.30.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
555
+ "decoder.model.layers.30.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
556
+ "decoder.model.layers.30.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
557
+ "decoder.model.layers.30.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
558
+ "decoder.model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
559
+ "decoder.model.layers.31.mlp.fc1.weight": "model-00003-of-00004.safetensors",
560
+ "decoder.model.layers.31.mlp.fc2.weight": "model-00003-of-00004.safetensors",
561
+ "decoder.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
562
+ "decoder.model.layers.31.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
563
+ "decoder.model.layers.31.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
564
+ "decoder.model.layers.31.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
565
+ "decoder.model.layers.31.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
566
+ "decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
567
+ "decoder.model.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
568
+ "decoder.model.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
570
+ "decoder.model.layers.4.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
571
+ "decoder.model.layers.4.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
572
+ "decoder.model.layers.4.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
573
+ "decoder.model.layers.4.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
574
+ "decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
575
+ "decoder.model.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
576
+ "decoder.model.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
577
+ "decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
578
+ "decoder.model.layers.5.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
579
+ "decoder.model.layers.5.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
580
+ "decoder.model.layers.5.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
581
+ "decoder.model.layers.5.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
582
+ "decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
583
+ "decoder.model.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
584
+ "decoder.model.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
585
+ "decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
586
+ "decoder.model.layers.6.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
587
+ "decoder.model.layers.6.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
588
+ "decoder.model.layers.6.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
589
+ "decoder.model.layers.6.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
590
+ "decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
591
+ "decoder.model.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
592
+ "decoder.model.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
593
+ "decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
594
+ "decoder.model.layers.7.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
595
+ "decoder.model.layers.7.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
596
+ "decoder.model.layers.7.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
597
+ "decoder.model.layers.7.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
598
+ "decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
599
+ "decoder.model.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
600
+ "decoder.model.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
602
+ "decoder.model.layers.8.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
603
+ "decoder.model.layers.8.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
604
+ "decoder.model.layers.8.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
605
+ "decoder.model.layers.8.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
606
+ "decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
607
+ "decoder.model.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
608
+ "decoder.model.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
609
+ "decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
610
+ "decoder.model.layers.9.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
611
+ "decoder.model.layers.9.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
612
+ "decoder.model.layers.9.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
613
+ "decoder.model.layers.9.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
614
+ "decoder.model.norm.weight": "model-00003-of-00004.safetensors",
615
+ "depth_decoder.embed_tokens.0.weight": "model-00003-of-00004.safetensors",
616
+ "depth_decoder.embed_tokens.1.weight": "model-00003-of-00004.safetensors",
617
+ "depth_decoder.embed_tokens.2.weight": "model-00003-of-00004.safetensors",
618
+ "depth_decoder.embed_tokens.3.weight": "model-00003-of-00004.safetensors",
619
+ "depth_decoder.embed_tokens.4.weight": "model-00003-of-00004.safetensors",
620
+ "depth_decoder.embed_tokens.5.weight": "model-00003-of-00004.safetensors",
621
+ "depth_decoder.embed_tokens.6.weight": "model-00003-of-00004.safetensors",
622
+ "depth_decoder.input_projections.weight": "model-00003-of-00004.safetensors",
623
+ "depth_decoder.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
624
+ "depth_decoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
625
+ "depth_decoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
626
+ "depth_decoder.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
627
+ "depth_decoder.layers.0.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
628
+ "depth_decoder.layers.0.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
629
+ "depth_decoder.layers.0.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
630
+ "depth_decoder.layers.0.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
631
+ "depth_decoder.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
632
+ "depth_decoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
633
+ "depth_decoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
634
+ "depth_decoder.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
635
+ "depth_decoder.layers.1.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
636
+ "depth_decoder.layers.1.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
637
+ "depth_decoder.layers.1.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
638
+ "depth_decoder.layers.1.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
639
+ "depth_decoder.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
640
+ "depth_decoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
641
+ "depth_decoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
642
+ "depth_decoder.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
643
+ "depth_decoder.layers.2.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
644
+ "depth_decoder.layers.2.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
645
+ "depth_decoder.layers.2.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
646
+ "depth_decoder.layers.2.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
647
+ "depth_decoder.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
648
+ "depth_decoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
649
+ "depth_decoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
650
+ "depth_decoder.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
651
+ "depth_decoder.layers.3.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
652
+ "depth_decoder.layers.3.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
653
+ "depth_decoder.layers.3.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
654
+ "depth_decoder.layers.3.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
655
+ "depth_decoder.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
656
+ "depth_decoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
657
+ "depth_decoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
658
+ "depth_decoder.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
659
+ "depth_decoder.layers.4.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
660
+ "depth_decoder.layers.4.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
661
+ "depth_decoder.layers.4.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
662
+ "depth_decoder.layers.4.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
663
+ "depth_decoder.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
664
+ "depth_decoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
665
+ "depth_decoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
666
+ "depth_decoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
667
+ "depth_decoder.layers.5.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
668
+ "depth_decoder.layers.5.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
669
+ "depth_decoder.layers.5.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
670
+ "depth_decoder.layers.5.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
671
+ "depth_decoder.lm_heads.weight": "model-00004-of-00004.safetensors",
672
+ "depth_decoder.text_embed_tokens.weight": "model-00003-of-00004.safetensors",
673
+ "embed_tokens.0.weight": "model-00001-of-00004.safetensors",
674
+ "embed_tokens.1.weight": "model-00001-of-00004.safetensors",
675
+ "embed_tokens.10.weight": "model-00001-of-00004.safetensors",
676
+ "embed_tokens.11.weight": "model-00001-of-00004.safetensors",
677
+ "embed_tokens.12.weight": "model-00001-of-00004.safetensors",
678
+ "embed_tokens.13.weight": "model-00001-of-00004.safetensors",
679
+ "embed_tokens.14.weight": "model-00001-of-00004.safetensors",
680
+ "embed_tokens.15.weight": "model-00001-of-00004.safetensors",
681
+ "embed_tokens.2.weight": "model-00001-of-00004.safetensors",
682
+ "embed_tokens.3.weight": "model-00001-of-00004.safetensors",
683
+ "embed_tokens.4.weight": "model-00001-of-00004.safetensors",
684
+ "embed_tokens.5.weight": "model-00001-of-00004.safetensors",
685
+ "embed_tokens.6.weight": "model-00001-of-00004.safetensors",
686
+ "embed_tokens.7.weight": "model-00001-of-00004.safetensors",
687
+ "embed_tokens.8.weight": "model-00001-of-00004.safetensors",
688
+ "embed_tokens.9.weight": "model-00001-of-00004.safetensors"
689
+ }
690
+ }