Laurent commited on
Commit
45e7a42
·
1 Parent(s): a2dc69b

Revert "transformers-integration (#2)"

Browse files

This reverts commit a2dc69b6c6d5e96a88da602d110dbd1a137d17a0.

README.md CHANGED
@@ -50,79 +50,6 @@ The predicted text token timestamps can be recovered by subtracting the model's
50
 
51
  See the [GitHub repository](https://github.com/kyutai-labs/delayed-streams-modeling/).
52
 
53
- ### Use with transformers
54
-
55
- Install transformers from source:
56
- ```bash
57
- pip install git+https://github.com/huggingface/transformers
58
- ```
59
-
60
- Inference:
61
- ```python
62
- import torch
63
- from datasets import load_dataset, Audio
64
- from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForConditionalGeneration
65
-
66
- # 1. load the model and the processor
67
- torch_device = "cuda" if torch.cuda.is_available() else "cpu"
68
- model_id = "kyutai/stt-2.6b-en"
69
-
70
- processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id)
71
- model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device)
72
-
73
- # 2. load audio samples
74
- ds = load_dataset(
75
- "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation"
76
- )
77
- ds = ds.cast_column("audio", Audio(sampling_rate=24000))
78
-
79
- # 3. prepare the model inputs
80
- inputs = processor(
81
- ds[0]["audio"]["array"],
82
- )
83
- inputs.to(torch_device)
84
-
85
- # 4. infer the model
86
- output_tokens = model.generate(**inputs)
87
-
88
- # 5. decode the generated tokens
89
- print(processor.batch_decode(output_tokens, skip_special_tokens=True))
90
- ```
91
-
92
- Batched inference:
93
- ```python
94
- import torch
95
- from datasets import load_dataset, Audio
96
- from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForConditionalGeneration
97
-
98
- # 1. load the model and the processor
99
- torch_device = "cuda" if torch.cuda.is_available() else "cpu"
100
- model_id = "kyutai/stt-2.6b-en"
101
-
102
- processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id)
103
- model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device)
104
-
105
- # 2. load audio samples
106
- ds = load_dataset(
107
- "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation"
108
- )
109
- ds = ds.cast_column("audio", Audio(sampling_rate=24000))
110
-
111
- # 3. prepare the model inputs
112
- audio_arrays = [ds[i]["audio"]["array"] for i in range(4)]
113
- inputs = processor(audio_arrays, return_tensors="pt", padding=True)
114
- inputs = inputs.to(torch_device)
115
-
116
- # 4. infer the model
117
- output_tokens = model.generate(**inputs)
118
-
119
- # 5. decode the generated tokens
120
- decoded_outputs = processor.batch_decode(output_tokens, skip_special_tokens=True)
121
- for output in decoded_outputs:
122
- print(output)
123
- ```
124
- ####
125
-
126
  ## Training Details
127
 
128
  ### Training Data
 
50
 
51
  See the [GitHub repository](https://github.com/kyutai-labs/delayed-streams-modeling/).
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  ## Training Details
54
 
55
  ### Training Data
config.json CHANGED
@@ -75,80 +75,5 @@
75
  },
76
  "model_type": "stt",
77
  "mimi_name": "[email protected]",
78
- "tokenizer_name": "tokenizer_en_audio_4000.model",
79
- "architectures": [
80
- "KyutaiSpeechToTextForConditionalGeneration"
81
- ],
82
- "attention_dropout": 0.0,
83
- "audio_bos_token_id": 2048,
84
- "audio_pad_token_id": 69569,
85
- "bos_token_id": 48000,
86
- "codebook_vocab_size": 2049,
87
- "codec_config": {
88
- "attention_bias": false,
89
- "attention_dropout": 0.0,
90
- "audio_channels": 1,
91
- "codebook_dim": 256,
92
- "codebook_size": 2048,
93
- "compress": 2,
94
- "dilation_growth_rate": 2,
95
- "frame_rate": 12.5,
96
- "head_dim": 64,
97
- "hidden_act": "gelu",
98
- "hidden_size": 512,
99
- "initializer_range": 0.02,
100
- "intermediate_size": 2048,
101
- "kernel_size": 7,
102
- "last_kernel_size": 3,
103
- "layer_scale_initial_scale": 0.01,
104
- "max_position_embeddings": 8000,
105
- "model_type": "mimi",
106
- "norm_eps": 1e-05,
107
- "num_attention_heads": 8,
108
- "num_filters": 64,
109
- "num_hidden_layers": 8,
110
- "num_key_value_heads": 8,
111
- "num_quantizers": 32,
112
- "num_residual_layers": 1,
113
- "num_semantic_quantizers": 1,
114
- "pad_mode": "constant",
115
- "residual_kernel_size": 3,
116
- "rope_theta": 10000.0,
117
- "sampling_rate": 24000,
118
- "sliding_window": 250,
119
- "trim_right_ratio": 1.0,
120
- "upsample_groups": 512,
121
- "upsampling_ratios": [
122
- 8,
123
- 6,
124
- 5,
125
- 4
126
- ],
127
- "use_cache": false,
128
- "use_causal_conv": true,
129
- "use_conv_shortcut": false,
130
- "use_streaming": false,
131
- "vector_quantization_hidden_dimension": 256
132
- },
133
- "ffn_dim": 11264,
134
- "frame_size": 1920,
135
- "head_dim": 64,
136
- "hidden_act": "silu",
137
- "hidden_size": 2048,
138
- "initializer_range": 0.02,
139
- "max_position_embeddings": 750,
140
- "num_attention_heads": 32,
141
- "num_codebooks": 32,
142
- "num_hidden_layers": 48,
143
- "num_key_value_heads": 32,
144
- "pad_token_id": 3,
145
- "rms_norm_eps": 1e-08,
146
- "rope_theta": 100000.0,
147
- "sliding_window": 375,
148
- "tie_word_embeddings": false,
149
- "torch_dtype": "bfloat16",
150
- "transformers_version": "4.53.0.dev0",
151
- "use_cache": true,
152
- "vocab_size": 4001,
153
- "transformers_weights": "transformers.safetensors.index.json"
154
  }
 
75
  },
76
  "model_type": "stt",
77
  "mimi_name": "[email protected]",
78
+ "tokenizer_name": "tokenizer_en_audio_4000.model"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  }
generation_config.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "audio_window_size": 1,
3
- "bos_token_id": 48000,
4
- "cache_implementation": "sliding_window",
5
- "codec_cache_implementation": "sliding_window",
6
- "codec_use_cache": true,
7
- "pad_token_id": 3,
8
- "transformers_version": "4.53.0.dev0"
9
- }
 
 
 
 
 
 
 
 
 
 
preprocessor_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "audio_delay_seconds": 2.5,
3
- "audio_silence_prefix_seconds": 1.0,
4
- "chunk_length_s": null,
5
- "feature_extractor_type": "KyutaiSpeechToTextFeatureExtractor",
6
- "feature_size": 1,
7
- "overlap": null,
8
- "padding_side": "right",
9
- "padding_value": 0.0,
10
- "processor_class": "KyutaiSpeechToTextProcessor",
11
- "return_attention_mask": true,
12
- "sampling_rate": 24000
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "unk_token": "<unk>"
3
- }
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1,50 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<unk>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<s>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<pad>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- }
35
- },
36
- "bos_token_id": null,
37
- "chat_template": null,
38
- "clean_up_tokenization_spaces": false,
39
- "eos_token_id": null,
40
- "extra_special_tokens": {},
41
- "model_input_names": [
42
- "input_ids",
43
- "attention_mask"
44
- ],
45
- "model_max_length": 1000000000000000019884624838656,
46
- "pad_token_id": null,
47
- "processor_class": "KyutaiSpeechToTextProcessor",
48
- "tokenizer_class": "PreTrainedTokenizerFast",
49
- "unk_token": "<unk>"
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
transformers-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d10da996924f8718e69ad188d65e4334f6c82a12bcaf8c5df83e80c9f5fca98b
3
- size 4372392344
 
 
 
 
transformers-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe01b3882f795cc9198c6e7f1fa4f08000e14f59ac8b181a294535ddb41cc33b
3
- size 1547899924
 
 
 
 
transformers.safetensors.index.json DELETED
@@ -1,745 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 2696431425,
4
- "total_size": 6759058820
5
- },
6
- "weight_map": {
7
- "codec_model.decoder.layers.0.conv.bias": "transformers-00002-of-00002.safetensors",
8
- "codec_model.decoder.layers.0.conv.weight": "transformers-00002-of-00002.safetensors",
9
- "codec_model.decoder.layers.11.conv.bias": "transformers-00002-of-00002.safetensors",
10
- "codec_model.decoder.layers.11.conv.weight": "transformers-00002-of-00002.safetensors",
11
- "codec_model.decoder.layers.12.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
12
- "codec_model.decoder.layers.12.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
13
- "codec_model.decoder.layers.12.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
14
- "codec_model.decoder.layers.12.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
15
- "codec_model.decoder.layers.14.conv.bias": "transformers-00002-of-00002.safetensors",
16
- "codec_model.decoder.layers.14.conv.weight": "transformers-00002-of-00002.safetensors",
17
- "codec_model.decoder.layers.2.conv.bias": "transformers-00002-of-00002.safetensors",
18
- "codec_model.decoder.layers.2.conv.weight": "transformers-00002-of-00002.safetensors",
19
- "codec_model.decoder.layers.3.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
20
- "codec_model.decoder.layers.3.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
21
- "codec_model.decoder.layers.3.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
22
- "codec_model.decoder.layers.3.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
23
- "codec_model.decoder.layers.5.conv.bias": "transformers-00002-of-00002.safetensors",
24
- "codec_model.decoder.layers.5.conv.weight": "transformers-00002-of-00002.safetensors",
25
- "codec_model.decoder.layers.6.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
26
- "codec_model.decoder.layers.6.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
27
- "codec_model.decoder.layers.6.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
28
- "codec_model.decoder.layers.6.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
29
- "codec_model.decoder.layers.8.conv.bias": "transformers-00002-of-00002.safetensors",
30
- "codec_model.decoder.layers.8.conv.weight": "transformers-00002-of-00002.safetensors",
31
- "codec_model.decoder.layers.9.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
32
- "codec_model.decoder.layers.9.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
33
- "codec_model.decoder.layers.9.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
34
- "codec_model.decoder.layers.9.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
35
- "codec_model.decoder_transformer.layers.0.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
36
- "codec_model.decoder_transformer.layers.0.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
37
- "codec_model.decoder_transformer.layers.0.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
38
- "codec_model.decoder_transformer.layers.0.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
39
- "codec_model.decoder_transformer.layers.0.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
40
- "codec_model.decoder_transformer.layers.0.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
41
- "codec_model.decoder_transformer.layers.0.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
42
- "codec_model.decoder_transformer.layers.0.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
43
- "codec_model.decoder_transformer.layers.0.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
44
- "codec_model.decoder_transformer.layers.0.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
45
- "codec_model.decoder_transformer.layers.0.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
46
- "codec_model.decoder_transformer.layers.0.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
47
- "codec_model.decoder_transformer.layers.1.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
48
- "codec_model.decoder_transformer.layers.1.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
49
- "codec_model.decoder_transformer.layers.1.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
50
- "codec_model.decoder_transformer.layers.1.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
51
- "codec_model.decoder_transformer.layers.1.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
52
- "codec_model.decoder_transformer.layers.1.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
53
- "codec_model.decoder_transformer.layers.1.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
54
- "codec_model.decoder_transformer.layers.1.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
55
- "codec_model.decoder_transformer.layers.1.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
56
- "codec_model.decoder_transformer.layers.1.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
57
- "codec_model.decoder_transformer.layers.1.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
58
- "codec_model.decoder_transformer.layers.1.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
59
- "codec_model.decoder_transformer.layers.2.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
60
- "codec_model.decoder_transformer.layers.2.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
61
- "codec_model.decoder_transformer.layers.2.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
62
- "codec_model.decoder_transformer.layers.2.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
63
- "codec_model.decoder_transformer.layers.2.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
64
- "codec_model.decoder_transformer.layers.2.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
65
- "codec_model.decoder_transformer.layers.2.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
66
- "codec_model.decoder_transformer.layers.2.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
67
- "codec_model.decoder_transformer.layers.2.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
68
- "codec_model.decoder_transformer.layers.2.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
69
- "codec_model.decoder_transformer.layers.2.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
70
- "codec_model.decoder_transformer.layers.2.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
71
- "codec_model.decoder_transformer.layers.3.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
72
- "codec_model.decoder_transformer.layers.3.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
73
- "codec_model.decoder_transformer.layers.3.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
74
- "codec_model.decoder_transformer.layers.3.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
75
- "codec_model.decoder_transformer.layers.3.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
76
- "codec_model.decoder_transformer.layers.3.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
77
- "codec_model.decoder_transformer.layers.3.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
78
- "codec_model.decoder_transformer.layers.3.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
79
- "codec_model.decoder_transformer.layers.3.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
80
- "codec_model.decoder_transformer.layers.3.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
81
- "codec_model.decoder_transformer.layers.3.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
82
- "codec_model.decoder_transformer.layers.3.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
83
- "codec_model.decoder_transformer.layers.4.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
84
- "codec_model.decoder_transformer.layers.4.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
85
- "codec_model.decoder_transformer.layers.4.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
86
- "codec_model.decoder_transformer.layers.4.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
87
- "codec_model.decoder_transformer.layers.4.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
88
- "codec_model.decoder_transformer.layers.4.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
89
- "codec_model.decoder_transformer.layers.4.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
90
- "codec_model.decoder_transformer.layers.4.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
91
- "codec_model.decoder_transformer.layers.4.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
92
- "codec_model.decoder_transformer.layers.4.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
93
- "codec_model.decoder_transformer.layers.4.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
94
- "codec_model.decoder_transformer.layers.4.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
95
- "codec_model.decoder_transformer.layers.5.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
96
- "codec_model.decoder_transformer.layers.5.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
97
- "codec_model.decoder_transformer.layers.5.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
98
- "codec_model.decoder_transformer.layers.5.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
99
- "codec_model.decoder_transformer.layers.5.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
100
- "codec_model.decoder_transformer.layers.5.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
101
- "codec_model.decoder_transformer.layers.5.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
102
- "codec_model.decoder_transformer.layers.5.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
103
- "codec_model.decoder_transformer.layers.5.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
104
- "codec_model.decoder_transformer.layers.5.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
105
- "codec_model.decoder_transformer.layers.5.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
106
- "codec_model.decoder_transformer.layers.5.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
107
- "codec_model.decoder_transformer.layers.6.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
108
- "codec_model.decoder_transformer.layers.6.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
109
- "codec_model.decoder_transformer.layers.6.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
110
- "codec_model.decoder_transformer.layers.6.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
111
- "codec_model.decoder_transformer.layers.6.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
112
- "codec_model.decoder_transformer.layers.6.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
113
- "codec_model.decoder_transformer.layers.6.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
114
- "codec_model.decoder_transformer.layers.6.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
115
- "codec_model.decoder_transformer.layers.6.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
116
- "codec_model.decoder_transformer.layers.6.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
117
- "codec_model.decoder_transformer.layers.6.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
118
- "codec_model.decoder_transformer.layers.6.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
119
- "codec_model.decoder_transformer.layers.7.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
120
- "codec_model.decoder_transformer.layers.7.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
121
- "codec_model.decoder_transformer.layers.7.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
122
- "codec_model.decoder_transformer.layers.7.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
123
- "codec_model.decoder_transformer.layers.7.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
124
- "codec_model.decoder_transformer.layers.7.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
125
- "codec_model.decoder_transformer.layers.7.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
126
- "codec_model.decoder_transformer.layers.7.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
127
- "codec_model.decoder_transformer.layers.7.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
128
- "codec_model.decoder_transformer.layers.7.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
129
- "codec_model.decoder_transformer.layers.7.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
130
- "codec_model.decoder_transformer.layers.7.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
131
- "codec_model.downsample.conv.weight": "transformers-00002-of-00002.safetensors",
132
- "codec_model.encoder.layers.0.conv.bias": "transformers-00002-of-00002.safetensors",
133
- "codec_model.encoder.layers.0.conv.weight": "transformers-00002-of-00002.safetensors",
134
- "codec_model.encoder.layers.1.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
135
- "codec_model.encoder.layers.1.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
136
- "codec_model.encoder.layers.1.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
137
- "codec_model.encoder.layers.1.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
138
- "codec_model.encoder.layers.10.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
139
- "codec_model.encoder.layers.10.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
140
- "codec_model.encoder.layers.10.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
141
- "codec_model.encoder.layers.10.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
142
- "codec_model.encoder.layers.12.conv.bias": "transformers-00002-of-00002.safetensors",
143
- "codec_model.encoder.layers.12.conv.weight": "transformers-00002-of-00002.safetensors",
144
- "codec_model.encoder.layers.14.conv.bias": "transformers-00002-of-00002.safetensors",
145
- "codec_model.encoder.layers.14.conv.weight": "transformers-00002-of-00002.safetensors",
146
- "codec_model.encoder.layers.3.conv.bias": "transformers-00002-of-00002.safetensors",
147
- "codec_model.encoder.layers.3.conv.weight": "transformers-00002-of-00002.safetensors",
148
- "codec_model.encoder.layers.4.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
149
- "codec_model.encoder.layers.4.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
150
- "codec_model.encoder.layers.4.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
151
- "codec_model.encoder.layers.4.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
152
- "codec_model.encoder.layers.6.conv.bias": "transformers-00002-of-00002.safetensors",
153
- "codec_model.encoder.layers.6.conv.weight": "transformers-00002-of-00002.safetensors",
154
- "codec_model.encoder.layers.7.block.1.conv.bias": "transformers-00002-of-00002.safetensors",
155
- "codec_model.encoder.layers.7.block.1.conv.weight": "transformers-00002-of-00002.safetensors",
156
- "codec_model.encoder.layers.7.block.3.conv.bias": "transformers-00002-of-00002.safetensors",
157
- "codec_model.encoder.layers.7.block.3.conv.weight": "transformers-00002-of-00002.safetensors",
158
- "codec_model.encoder.layers.9.conv.bias": "transformers-00002-of-00002.safetensors",
159
- "codec_model.encoder.layers.9.conv.weight": "transformers-00002-of-00002.safetensors",
160
- "codec_model.encoder_transformer.layers.0.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
161
- "codec_model.encoder_transformer.layers.0.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
162
- "codec_model.encoder_transformer.layers.0.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
163
- "codec_model.encoder_transformer.layers.0.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
164
- "codec_model.encoder_transformer.layers.0.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
165
- "codec_model.encoder_transformer.layers.0.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
166
- "codec_model.encoder_transformer.layers.0.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
167
- "codec_model.encoder_transformer.layers.0.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
168
- "codec_model.encoder_transformer.layers.0.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
169
- "codec_model.encoder_transformer.layers.0.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
170
- "codec_model.encoder_transformer.layers.0.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
171
- "codec_model.encoder_transformer.layers.0.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
172
- "codec_model.encoder_transformer.layers.1.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
173
- "codec_model.encoder_transformer.layers.1.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
174
- "codec_model.encoder_transformer.layers.1.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
175
- "codec_model.encoder_transformer.layers.1.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
176
- "codec_model.encoder_transformer.layers.1.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
177
- "codec_model.encoder_transformer.layers.1.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
178
- "codec_model.encoder_transformer.layers.1.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
179
- "codec_model.encoder_transformer.layers.1.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
180
- "codec_model.encoder_transformer.layers.1.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
181
- "codec_model.encoder_transformer.layers.1.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
182
- "codec_model.encoder_transformer.layers.1.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
183
- "codec_model.encoder_transformer.layers.1.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
184
- "codec_model.encoder_transformer.layers.2.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
185
- "codec_model.encoder_transformer.layers.2.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
186
- "codec_model.encoder_transformer.layers.2.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
187
- "codec_model.encoder_transformer.layers.2.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
188
- "codec_model.encoder_transformer.layers.2.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
189
- "codec_model.encoder_transformer.layers.2.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
190
- "codec_model.encoder_transformer.layers.2.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
191
- "codec_model.encoder_transformer.layers.2.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
192
- "codec_model.encoder_transformer.layers.2.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
193
- "codec_model.encoder_transformer.layers.2.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
194
- "codec_model.encoder_transformer.layers.2.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
195
- "codec_model.encoder_transformer.layers.2.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
196
- "codec_model.encoder_transformer.layers.3.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
197
- "codec_model.encoder_transformer.layers.3.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
198
- "codec_model.encoder_transformer.layers.3.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
199
- "codec_model.encoder_transformer.layers.3.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
200
- "codec_model.encoder_transformer.layers.3.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
201
- "codec_model.encoder_transformer.layers.3.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
202
- "codec_model.encoder_transformer.layers.3.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
203
- "codec_model.encoder_transformer.layers.3.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
204
- "codec_model.encoder_transformer.layers.3.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
205
- "codec_model.encoder_transformer.layers.3.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
206
- "codec_model.encoder_transformer.layers.3.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
207
- "codec_model.encoder_transformer.layers.3.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
208
- "codec_model.encoder_transformer.layers.4.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
209
- "codec_model.encoder_transformer.layers.4.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
210
- "codec_model.encoder_transformer.layers.4.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
211
- "codec_model.encoder_transformer.layers.4.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
212
- "codec_model.encoder_transformer.layers.4.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
213
- "codec_model.encoder_transformer.layers.4.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
214
- "codec_model.encoder_transformer.layers.4.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
215
- "codec_model.encoder_transformer.layers.4.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
216
- "codec_model.encoder_transformer.layers.4.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
217
- "codec_model.encoder_transformer.layers.4.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
218
- "codec_model.encoder_transformer.layers.4.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
219
- "codec_model.encoder_transformer.layers.4.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
220
- "codec_model.encoder_transformer.layers.5.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
221
- "codec_model.encoder_transformer.layers.5.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
222
- "codec_model.encoder_transformer.layers.5.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
223
- "codec_model.encoder_transformer.layers.5.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
224
- "codec_model.encoder_transformer.layers.5.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
225
- "codec_model.encoder_transformer.layers.5.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
226
- "codec_model.encoder_transformer.layers.5.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
227
- "codec_model.encoder_transformer.layers.5.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
228
- "codec_model.encoder_transformer.layers.5.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
229
- "codec_model.encoder_transformer.layers.5.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
230
- "codec_model.encoder_transformer.layers.5.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
231
- "codec_model.encoder_transformer.layers.5.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
232
- "codec_model.encoder_transformer.layers.6.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
233
- "codec_model.encoder_transformer.layers.6.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
234
- "codec_model.encoder_transformer.layers.6.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
235
- "codec_model.encoder_transformer.layers.6.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
236
- "codec_model.encoder_transformer.layers.6.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
237
- "codec_model.encoder_transformer.layers.6.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
238
- "codec_model.encoder_transformer.layers.6.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
239
- "codec_model.encoder_transformer.layers.6.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
240
- "codec_model.encoder_transformer.layers.6.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
241
- "codec_model.encoder_transformer.layers.6.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
242
- "codec_model.encoder_transformer.layers.6.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
243
- "codec_model.encoder_transformer.layers.6.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
244
- "codec_model.encoder_transformer.layers.7.input_layernorm.bias": "transformers-00002-of-00002.safetensors",
245
- "codec_model.encoder_transformer.layers.7.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
246
- "codec_model.encoder_transformer.layers.7.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
247
- "codec_model.encoder_transformer.layers.7.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
248
- "codec_model.encoder_transformer.layers.7.mlp_layer_scale.scale": "transformers-00002-of-00002.safetensors",
249
- "codec_model.encoder_transformer.layers.7.post_attention_layernorm.bias": "transformers-00002-of-00002.safetensors",
250
- "codec_model.encoder_transformer.layers.7.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
251
- "codec_model.encoder_transformer.layers.7.self_attn.k_proj.weight": "transformers-00002-of-00002.safetensors",
252
- "codec_model.encoder_transformer.layers.7.self_attn.o_proj.weight": "transformers-00002-of-00002.safetensors",
253
- "codec_model.encoder_transformer.layers.7.self_attn.q_proj.weight": "transformers-00002-of-00002.safetensors",
254
- "codec_model.encoder_transformer.layers.7.self_attn.v_proj.weight": "transformers-00002-of-00002.safetensors",
255
- "codec_model.encoder_transformer.layers.7.self_attn_layer_scale.scale": "transformers-00002-of-00002.safetensors",
256
- "codec_model.quantizer.acoustic_residual_vector_quantizer.input_proj.weight": "transformers-00002-of-00002.safetensors",
257
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
258
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
259
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.initialized": "transformers-00002-of-00002.safetensors",
260
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
261
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
262
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.initialized": "transformers-00002-of-00002.safetensors",
263
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
264
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
265
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.initialized": "transformers-00002-of-00002.safetensors",
266
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
267
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
268
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.initialized": "transformers-00002-of-00002.safetensors",
269
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
270
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
271
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.initialized": "transformers-00002-of-00002.safetensors",
272
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
273
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
274
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.initialized": "transformers-00002-of-00002.safetensors",
275
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
276
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
277
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.initialized": "transformers-00002-of-00002.safetensors",
278
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
279
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
280
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.initialized": "transformers-00002-of-00002.safetensors",
281
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
282
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
283
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.initialized": "transformers-00002-of-00002.safetensors",
284
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
285
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
286
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.initialized": "transformers-00002-of-00002.safetensors",
287
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
288
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
289
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.initialized": "transformers-00002-of-00002.safetensors",
290
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
291
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
292
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.initialized": "transformers-00002-of-00002.safetensors",
293
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
294
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
295
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.initialized": "transformers-00002-of-00002.safetensors",
296
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
297
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
298
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.initialized": "transformers-00002-of-00002.safetensors",
299
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
300
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
301
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.initialized": "transformers-00002-of-00002.safetensors",
302
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
303
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
304
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.initialized": "transformers-00002-of-00002.safetensors",
305
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
306
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
307
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.initialized": "transformers-00002-of-00002.safetensors",
308
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
309
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
310
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.initialized": "transformers-00002-of-00002.safetensors",
311
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
312
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
313
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.initialized": "transformers-00002-of-00002.safetensors",
314
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
315
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
316
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.initialized": "transformers-00002-of-00002.safetensors",
317
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
318
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
319
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.initialized": "transformers-00002-of-00002.safetensors",
320
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
321
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
322
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.initialized": "transformers-00002-of-00002.safetensors",
323
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
324
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
325
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.initialized": "transformers-00002-of-00002.safetensors",
326
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
327
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
328
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.initialized": "transformers-00002-of-00002.safetensors",
329
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
330
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
331
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.initialized": "transformers-00002-of-00002.safetensors",
332
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
333
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
334
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.initialized": "transformers-00002-of-00002.safetensors",
335
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
336
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
337
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.initialized": "transformers-00002-of-00002.safetensors",
338
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
339
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
340
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.initialized": "transformers-00002-of-00002.safetensors",
341
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
342
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
343
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.initialized": "transformers-00002-of-00002.safetensors",
344
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
345
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
346
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.initialized": "transformers-00002-of-00002.safetensors",
347
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
348
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
349
- "codec_model.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.initialized": "transformers-00002-of-00002.safetensors",
350
- "codec_model.quantizer.acoustic_residual_vector_quantizer.output_proj.weight": "transformers-00002-of-00002.safetensors",
351
- "codec_model.quantizer.semantic_residual_vector_quantizer.input_proj.weight": "transformers-00002-of-00002.safetensors",
352
- "codec_model.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.cluster_usage": "transformers-00002-of-00002.safetensors",
353
- "codec_model.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.embed_sum": "transformers-00002-of-00002.safetensors",
354
- "codec_model.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.initialized": "transformers-00002-of-00002.safetensors",
355
- "codec_model.quantizer.semantic_residual_vector_quantizer.output_proj.weight": "transformers-00002-of-00002.safetensors",
356
- "codec_model.upsample.conv.weight": "transformers-00002-of-00002.safetensors",
357
- "lm_head.weight": "transformers-00002-of-00002.safetensors",
358
- "model.embed_tokens.embed_tokens.weight": "transformers-00001-of-00002.safetensors",
359
- "model.layers.0.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
360
- "model.layers.0.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
361
- "model.layers.0.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
362
- "model.layers.0.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
363
- "model.layers.0.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
364
- "model.layers.0.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
365
- "model.layers.0.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
366
- "model.layers.0.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
367
- "model.layers.1.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
368
- "model.layers.1.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
369
- "model.layers.1.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
370
- "model.layers.1.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
371
- "model.layers.1.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
372
- "model.layers.1.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
373
- "model.layers.1.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
374
- "model.layers.1.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
375
- "model.layers.10.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
376
- "model.layers.10.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
377
- "model.layers.10.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
378
- "model.layers.10.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
379
- "model.layers.10.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
380
- "model.layers.10.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
381
- "model.layers.10.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
382
- "model.layers.10.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
383
- "model.layers.11.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
384
- "model.layers.11.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
385
- "model.layers.11.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
386
- "model.layers.11.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
387
- "model.layers.11.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
388
- "model.layers.11.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
389
- "model.layers.11.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
390
- "model.layers.11.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
391
- "model.layers.12.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
392
- "model.layers.12.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
393
- "model.layers.12.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
394
- "model.layers.12.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
395
- "model.layers.12.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
396
- "model.layers.12.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
397
- "model.layers.12.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
398
- "model.layers.12.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
399
- "model.layers.13.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
400
- "model.layers.13.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
401
- "model.layers.13.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
402
- "model.layers.13.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
403
- "model.layers.13.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
404
- "model.layers.13.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
405
- "model.layers.13.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
406
- "model.layers.13.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
407
- "model.layers.14.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
408
- "model.layers.14.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
409
- "model.layers.14.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
410
- "model.layers.14.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
411
- "model.layers.14.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
412
- "model.layers.14.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
413
- "model.layers.14.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
414
- "model.layers.14.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
415
- "model.layers.15.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
416
- "model.layers.15.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
417
- "model.layers.15.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
418
- "model.layers.15.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
419
- "model.layers.15.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
420
- "model.layers.15.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
421
- "model.layers.15.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
422
- "model.layers.15.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
423
- "model.layers.16.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
424
- "model.layers.16.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
425
- "model.layers.16.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
426
- "model.layers.16.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
427
- "model.layers.16.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
428
- "model.layers.16.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
429
- "model.layers.16.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
430
- "model.layers.16.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
431
- "model.layers.17.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
432
- "model.layers.17.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
433
- "model.layers.17.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
434
- "model.layers.17.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
435
- "model.layers.17.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
436
- "model.layers.17.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
437
- "model.layers.17.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
438
- "model.layers.17.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
439
- "model.layers.18.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
440
- "model.layers.18.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
441
- "model.layers.18.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
442
- "model.layers.18.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
443
- "model.layers.18.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
444
- "model.layers.18.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
445
- "model.layers.18.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
446
- "model.layers.18.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
447
- "model.layers.19.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
448
- "model.layers.19.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
449
- "model.layers.19.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
450
- "model.layers.19.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
451
- "model.layers.19.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
452
- "model.layers.19.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
453
- "model.layers.19.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
454
- "model.layers.19.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
455
- "model.layers.2.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
456
- "model.layers.2.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
457
- "model.layers.2.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
458
- "model.layers.2.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
459
- "model.layers.2.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
460
- "model.layers.2.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
461
- "model.layers.2.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
462
- "model.layers.2.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
463
- "model.layers.20.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
464
- "model.layers.20.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
465
- "model.layers.20.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
466
- "model.layers.20.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
467
- "model.layers.20.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
468
- "model.layers.20.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
469
- "model.layers.20.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
470
- "model.layers.20.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
471
- "model.layers.21.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
472
- "model.layers.21.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
473
- "model.layers.21.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
474
- "model.layers.21.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
475
- "model.layers.21.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
476
- "model.layers.21.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
477
- "model.layers.21.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
478
- "model.layers.21.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
479
- "model.layers.22.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
480
- "model.layers.22.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
481
- "model.layers.22.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
482
- "model.layers.22.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
483
- "model.layers.22.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
484
- "model.layers.22.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
485
- "model.layers.22.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
486
- "model.layers.22.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
487
- "model.layers.23.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
488
- "model.layers.23.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
489
- "model.layers.23.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
490
- "model.layers.23.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
491
- "model.layers.23.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
492
- "model.layers.23.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
493
- "model.layers.23.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
494
- "model.layers.23.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
495
- "model.layers.24.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
496
- "model.layers.24.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
497
- "model.layers.24.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
498
- "model.layers.24.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
499
- "model.layers.24.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
500
- "model.layers.24.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
501
- "model.layers.24.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
502
- "model.layers.24.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
503
- "model.layers.25.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
504
- "model.layers.25.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
505
- "model.layers.25.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
506
- "model.layers.25.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
507
- "model.layers.25.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
508
- "model.layers.25.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
509
- "model.layers.25.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
510
- "model.layers.25.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
511
- "model.layers.26.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
512
- "model.layers.26.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
513
- "model.layers.26.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
514
- "model.layers.26.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
515
- "model.layers.26.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
516
- "model.layers.26.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
517
- "model.layers.26.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
518
- "model.layers.26.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
519
- "model.layers.27.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
520
- "model.layers.27.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
521
- "model.layers.27.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
522
- "model.layers.27.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
523
- "model.layers.27.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
524
- "model.layers.27.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
525
- "model.layers.27.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
526
- "model.layers.27.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
527
- "model.layers.28.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
528
- "model.layers.28.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
529
- "model.layers.28.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
530
- "model.layers.28.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
531
- "model.layers.28.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
532
- "model.layers.28.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
533
- "model.layers.28.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
534
- "model.layers.28.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
535
- "model.layers.29.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
536
- "model.layers.29.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
537
- "model.layers.29.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
538
- "model.layers.29.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
539
- "model.layers.29.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
540
- "model.layers.29.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
541
- "model.layers.29.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
542
- "model.layers.29.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
543
- "model.layers.3.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
544
- "model.layers.3.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
545
- "model.layers.3.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
546
- "model.layers.3.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
547
- "model.layers.3.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
548
- "model.layers.3.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
549
- "model.layers.3.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
550
- "model.layers.3.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
551
- "model.layers.30.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
552
- "model.layers.30.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
553
- "model.layers.30.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
554
- "model.layers.30.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
555
- "model.layers.30.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
556
- "model.layers.30.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
557
- "model.layers.30.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
558
- "model.layers.30.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
559
- "model.layers.31.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
560
- "model.layers.31.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
561
- "model.layers.31.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
562
- "model.layers.31.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
563
- "model.layers.31.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
564
- "model.layers.31.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
565
- "model.layers.31.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
566
- "model.layers.31.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
567
- "model.layers.32.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
568
- "model.layers.32.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
569
- "model.layers.32.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
570
- "model.layers.32.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
571
- "model.layers.32.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
572
- "model.layers.32.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
573
- "model.layers.32.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
574
- "model.layers.32.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
575
- "model.layers.33.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
576
- "model.layers.33.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
577
- "model.layers.33.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
578
- "model.layers.33.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
579
- "model.layers.33.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
580
- "model.layers.33.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
581
- "model.layers.33.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
582
- "model.layers.33.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
583
- "model.layers.34.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
584
- "model.layers.34.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
585
- "model.layers.34.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
586
- "model.layers.34.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
587
- "model.layers.34.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
588
- "model.layers.34.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
589
- "model.layers.34.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
590
- "model.layers.34.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
591
- "model.layers.35.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
592
- "model.layers.35.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
593
- "model.layers.35.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
594
- "model.layers.35.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
595
- "model.layers.35.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
596
- "model.layers.35.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
597
- "model.layers.35.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
598
- "model.layers.35.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
599
- "model.layers.36.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
600
- "model.layers.36.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
601
- "model.layers.36.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
602
- "model.layers.36.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
603
- "model.layers.36.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
604
- "model.layers.36.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
605
- "model.layers.36.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
606
- "model.layers.36.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
607
- "model.layers.37.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
608
- "model.layers.37.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
609
- "model.layers.37.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
610
- "model.layers.37.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
611
- "model.layers.37.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
612
- "model.layers.37.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
613
- "model.layers.37.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
614
- "model.layers.37.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
615
- "model.layers.38.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
616
- "model.layers.38.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
617
- "model.layers.38.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
618
- "model.layers.38.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
619
- "model.layers.38.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
620
- "model.layers.38.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
621
- "model.layers.38.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
622
- "model.layers.38.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
623
- "model.layers.39.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
624
- "model.layers.39.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
625
- "model.layers.39.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
626
- "model.layers.39.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
627
- "model.layers.39.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
628
- "model.layers.39.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
629
- "model.layers.39.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
630
- "model.layers.39.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
631
- "model.layers.4.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
632
- "model.layers.4.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
633
- "model.layers.4.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
634
- "model.layers.4.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
635
- "model.layers.4.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
636
- "model.layers.4.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
637
- "model.layers.4.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
638
- "model.layers.4.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
639
- "model.layers.40.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
640
- "model.layers.40.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
641
- "model.layers.40.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
642
- "model.layers.40.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
643
- "model.layers.40.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
644
- "model.layers.40.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
645
- "model.layers.40.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
646
- "model.layers.40.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
647
- "model.layers.41.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
648
- "model.layers.41.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
649
- "model.layers.41.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
650
- "model.layers.41.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
651
- "model.layers.41.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
652
- "model.layers.41.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
653
- "model.layers.41.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
654
- "model.layers.41.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
655
- "model.layers.42.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
656
- "model.layers.42.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
657
- "model.layers.42.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
658
- "model.layers.42.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
659
- "model.layers.42.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
660
- "model.layers.42.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
661
- "model.layers.42.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
662
- "model.layers.42.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
663
- "model.layers.43.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
664
- "model.layers.43.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
665
- "model.layers.43.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
666
- "model.layers.43.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
667
- "model.layers.43.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
668
- "model.layers.43.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
669
- "model.layers.43.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
670
- "model.layers.43.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
671
- "model.layers.44.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
672
- "model.layers.44.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
673
- "model.layers.44.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
674
- "model.layers.44.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
675
- "model.layers.44.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
676
- "model.layers.44.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
677
- "model.layers.44.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
678
- "model.layers.44.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
679
- "model.layers.45.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
680
- "model.layers.45.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
681
- "model.layers.45.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
682
- "model.layers.45.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
683
- "model.layers.45.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
684
- "model.layers.45.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
685
- "model.layers.45.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
686
- "model.layers.45.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
687
- "model.layers.46.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
688
- "model.layers.46.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
689
- "model.layers.46.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
690
- "model.layers.46.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
691
- "model.layers.46.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
692
- "model.layers.46.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
693
- "model.layers.46.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
694
- "model.layers.46.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
695
- "model.layers.47.input_layernorm.weight": "transformers-00002-of-00002.safetensors",
696
- "model.layers.47.mlp.fc1.weight": "transformers-00002-of-00002.safetensors",
697
- "model.layers.47.mlp.fc2.weight": "transformers-00002-of-00002.safetensors",
698
- "model.layers.47.post_attention_layernorm.weight": "transformers-00002-of-00002.safetensors",
699
- "model.layers.47.self_attn.k_proj.linear.weight": "transformers-00002-of-00002.safetensors",
700
- "model.layers.47.self_attn.o_proj.linear.weight": "transformers-00002-of-00002.safetensors",
701
- "model.layers.47.self_attn.q_proj.linear.weight": "transformers-00002-of-00002.safetensors",
702
- "model.layers.47.self_attn.v_proj.linear.weight": "transformers-00002-of-00002.safetensors",
703
- "model.layers.5.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
704
- "model.layers.5.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
705
- "model.layers.5.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
706
- "model.layers.5.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
707
- "model.layers.5.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
708
- "model.layers.5.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
709
- "model.layers.5.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
710
- "model.layers.5.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
711
- "model.layers.6.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
712
- "model.layers.6.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
713
- "model.layers.6.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
714
- "model.layers.6.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
715
- "model.layers.6.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
716
- "model.layers.6.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
717
- "model.layers.6.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
718
- "model.layers.6.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
719
- "model.layers.7.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
720
- "model.layers.7.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
721
- "model.layers.7.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
722
- "model.layers.7.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
723
- "model.layers.7.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
724
- "model.layers.7.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
725
- "model.layers.7.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
726
- "model.layers.7.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
727
- "model.layers.8.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
728
- "model.layers.8.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
729
- "model.layers.8.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
730
- "model.layers.8.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
731
- "model.layers.8.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
732
- "model.layers.8.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
733
- "model.layers.8.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
734
- "model.layers.8.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
735
- "model.layers.9.input_layernorm.weight": "transformers-00001-of-00002.safetensors",
736
- "model.layers.9.mlp.fc1.weight": "transformers-00001-of-00002.safetensors",
737
- "model.layers.9.mlp.fc2.weight": "transformers-00001-of-00002.safetensors",
738
- "model.layers.9.post_attention_layernorm.weight": "transformers-00001-of-00002.safetensors",
739
- "model.layers.9.self_attn.k_proj.linear.weight": "transformers-00001-of-00002.safetensors",
740
- "model.layers.9.self_attn.o_proj.linear.weight": "transformers-00001-of-00002.safetensors",
741
- "model.layers.9.self_attn.q_proj.linear.weight": "transformers-00001-of-00002.safetensors",
742
- "model.layers.9.self_attn.v_proj.linear.weight": "transformers-00001-of-00002.safetensors",
743
- "model.norm.weight": "transformers-00002-of-00002.safetensors"
744
- }
745
- }