Hugging Face's logo

mlx-community
/
Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit

Text-to-Speech
Safetensors
Qwen3-TTS
MLX
mlx-audio
speech
speech generation
voice cloning
tts
8-bit precision
Model card Files
xet
 Community
1
prince-canuma commited on
Commit
5ab5394
·
verified ·
1 Parent(s): 9263bb0

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. README.md +43 -0
  2. config.json +193 -0
  3. generation_config.json +12 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +946 -0
  7. preprocessor_config.json +6 -0
  8. speech_tokenizer/config.json +94 -0
  9. speech_tokenizer/configuration.json +1 -0
  10. speech_tokenizer/model.safetensors +3 -0
  11. speech_tokenizer/preprocessor_config.json +10 -0
  12. tokenizer_config.json +316 -0
  13. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: mlx-audio
4
+ tags:
5
+ - mlx
6
+ - text-to-speech
7
+ - speech
8
+ - speech generation
9
+ - voice cloning
10
+ - tts
11
+ - mlx-audio
12
+ ---
13
+ # mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
14
+
15
+ This model was converted to MLX format from [`Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) using mlx-audio version **0.3.0rc1**.
16
+
17
+ Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) for more details on the model.
18
+
19
+ ## Use with mlx-audio
20
+
21
+ ```bash
22
+ pip install -U mlx-audio
23
+ ```
24
+
25
+ ### CLI Example:
26
+ ```bash
27
+ python -m mlx_audio.tts.generate --model mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit --text "Hello, this is a test."
28
+ ```
29
+
30
+ ### Python Example:
31
+ ```python
32
+ from mlx_audio.tts.utils import load_model
33
+ from mlx_audio.tts.generate import generate_audio
34
+
35
+ model = load_model("mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit")
36
+ generate_audio(
37
+ model=model,
38
+ text="Hello, this is a test.",
39
+ ref_audio="path_to_audio.wav",
40
+ file_prefix="test_audio",
41
+ )
42
+
43
+ ```
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3TTSForConditionalGeneration"
4
+ ],
5
+ "assistant_token_id": 77091,
6
+ "im_end_token_id": 151645,
7
+ "im_start_token_id": 151644,
8
+ "model_type": "qwen3_tts",
9
+ "quantization": {
10
+ "group_size": 64,
11
+ "bits": 8,
12
+ "mode": "affine"
13
+ },
14
+ "quantization_config": {
15
+ "group_size": 64,
16
+ "bits": 8,
17
+ "mode": "affine"
18
+ },
19
+ "talker_config": {
20
+ "attention_bias": false,
21
+ "attention_dropout": 0,
22
+ "code_predictor_config": {
23
+ "_name_or_path": "",
24
+ "add_cross_attention": false,
25
+ "architectures": null,
26
+ "attention_bias": false,
27
+ "attention_dropout": 0,
28
+ "bad_words_ids": null,
29
+ "begin_suppress_tokens": null,
30
+ "bos_token_id": null,
31
+ "chunk_size_feed_forward": 0,
32
+ "cross_attention_hidden_size": null,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": null,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "head_dim": 128,
44
+ "hidden_act": "silu",
45
+ "hidden_size": 1024,
46
+ "id2label": {
47
+ "0": "LABEL_0",
48
+ "1": "LABEL_1"
49
+ },
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "is_decoder": false,
53
+ "is_encoder_decoder": false,
54
+ "label2id": {
55
+ "LABEL_0": 0,
56
+ "LABEL_1": 1
57
+ },
58
+ "layer_types": [
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention"
64
+ ],
65
+ "length_penalty": 1.0,
66
+ "max_length": 20,
67
+ "max_position_embeddings": 65536,
68
+ "max_window_layers": 28,
69
+ "min_length": 0,
70
+ "model_type": "qwen3_tts_talker_code_predictor",
71
+ "no_repeat_ngram_size": 0,
72
+ "num_attention_heads": 16,
73
+ "num_beam_groups": 1,
74
+ "num_beams": 1,
75
+ "num_code_groups": 16,
76
+ "num_hidden_layers": 5,
77
+ "num_key_value_heads": 8,
78
+ "num_return_sequences": 1,
79
+ "output_attentions": false,
80
+ "output_hidden_states": false,
81
+ "output_scores": false,
82
+ "pad_token_id": null,
83
+ "prefix": null,
84
+ "problem_type": null,
85
+ "pruned_heads": {},
86
+ "remove_invalid_values": false,
87
+ "repetition_penalty": 1.0,
88
+ "return_dict": true,
89
+ "return_dict_in_generate": false,
90
+ "rms_norm_eps": 1e-06,
91
+ "rope_scaling": null,
92
+ "rope_theta": 1000000,
93
+ "sep_token_id": null,
94
+ "sliding_window": null,
95
+ "suppress_tokens": null,
96
+ "task_specific_params": null,
97
+ "temperature": 1.0,
98
+ "tf_legacy_loss": false,
99
+ "tie_encoder_decoder": false,
100
+ "tie_word_embeddings": false,
101
+ "tokenizer_class": null,
102
+ "top_k": 50,
103
+ "top_p": 1.0,
104
+ "dtype": null,
105
+ "torchscript": false,
106
+ "typical_p": 1.0,
107
+ "use_bfloat16": false,
108
+ "use_cache": true,
109
+ "use_sliding_window": false,
110
+ "vocab_size": 2048
111
+ },
112
+ "codec_bos_id": 2149,
113
+ "codec_eos_token_id": 2150,
114
+ "codec_think_id": 2154,
115
+ "codec_language_id": {
116
+ "chinese": 2055,
117
+ "english": 2050,
118
+ "german": 2053,
119
+ "italian": 2070,
120
+ "portuguese": 2071,
121
+ "spanish": 2054,
122
+ "japanese": 2058,
123
+ "korean": 2064,
124
+ "french": 2061,
125
+ "russian": 2069,
126
+ "beijing_dialect": 2074,
127
+ "sichuan_dialect": 2062
128
+ },
129
+ "codec_nothink_id": 2155,
130
+ "codec_pad_id": 2148,
131
+ "codec_think_bos_id": 2156,
132
+ "codec_think_eos_id": 2157,
133
+ "spk_id": {
134
+ "serena": 3066,
135
+ "vivian": 3065,
136
+ "uncle_fu": 3010,
137
+ "ryan": 3061,
138
+ "aiden": 2861,
139
+ "ono_anna": 2873,
140
+ "sohee": 2864,
141
+ "eric": 2875,
142
+ "dylan": 2878
143
+ },
144
+ "spk_is_dialect": {
145
+ "serena": false,
146
+ "vivian": false,
147
+ "uncle_fu": false,
148
+ "ryan": false,
149
+ "aiden": false,
150
+ "ono_anna": false,
151
+ "sohee": false,
152
+ "eric": "sichuan_dialect",
153
+ "dylan": "beijing_dialect"
154
+ },
155
+ "head_dim": 128,
156
+ "hidden_act": "silu",
157
+ "hidden_size": 2048,
158
+ "initializer_range": 0.02,
159
+ "intermediate_size": 6144,
160
+ "max_position_embeddings": 32768,
161
+ "model_type": "qwen3_tts_talker",
162
+ "num_attention_heads": 16,
163
+ "num_code_groups": 16,
164
+ "num_hidden_layers": 28,
165
+ "num_key_value_heads": 8,
166
+ "position_id_per_seconds": 13,
167
+ "rms_norm_eps": 1e-06,
168
+ "rope_scaling": {
169
+ "interleaved": true,
170
+ "mrope_section": [
171
+ 24,
172
+ 20,
173
+ 20
174
+ ],
175
+ "rope_type": "default",
176
+ "type": "default"
177
+ },
178
+ "rope_theta": 1000000,
179
+ "sliding_window": null,
180
+ "text_hidden_size": 2048,
181
+ "text_vocab_size": 151936,
182
+ "use_cache": true,
183
+ "use_sliding_window": false,
184
+ "vocab_size": 3072
185
+ },
186
+ "tokenizer_type": "qwen3_tts_tokenizer_12hz",
187
+ "transformers_version": "4.57.3",
188
+ "tts_bos_token_id": 151672,
189
+ "tts_eos_token_id": 151673,
190
+ "tts_model_size": "1b7",
191
+ "tts_model_type": "custom_voice",
192
+ "tts_pad_token_id": 151671
193
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "repetition_penalty": 1.05,
4
+ "temperature": 0.9,
5
+ "top_p": 1.0,
6
+ "top_k": 50,
7
+ "subtalker_dosample": true,
8
+ "subtalker_temperature": 0.9,
9
+ "subtalker_top_p": 1.0,
10
+ "subtalker_top_k": 50,
11
+ "max_new_tokens": 8192
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33518008c2920b3f4dcc829900cf3a3f670ba9da693c28b24371114e9f58cee0
3
+ size 2036715355
model.safetensors.index.json ADDED
@@ -0,0 +1,946 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2036601344,
4
+ "total_parameters": 1916676352
5
+ },
6
+ "weight_map": {
7
+ "talker.code_predictor.lm_head.0.biases": "model.safetensors",
8
+ "talker.code_predictor.lm_head.0.scales": "model.safetensors",
9
+ "talker.code_predictor.lm_head.0.weight": "model.safetensors",
10
+ "talker.code_predictor.lm_head.1.biases": "model.safetensors",
11
+ "talker.code_predictor.lm_head.1.scales": "model.safetensors",
12
+ "talker.code_predictor.lm_head.1.weight": "model.safetensors",
13
+ "talker.code_predictor.lm_head.10.biases": "model.safetensors",
14
+ "talker.code_predictor.lm_head.10.scales": "model.safetensors",
15
+ "talker.code_predictor.lm_head.10.weight": "model.safetensors",
16
+ "talker.code_predictor.lm_head.11.biases": "model.safetensors",
17
+ "talker.code_predictor.lm_head.11.scales": "model.safetensors",
18
+ "talker.code_predictor.lm_head.11.weight": "model.safetensors",
19
+ "talker.code_predictor.lm_head.12.biases": "model.safetensors",
20
+ "talker.code_predictor.lm_head.12.scales": "model.safetensors",
21
+ "talker.code_predictor.lm_head.12.weight": "model.safetensors",
22
+ "talker.code_predictor.lm_head.13.biases": "model.safetensors",
23
+ "talker.code_predictor.lm_head.13.scales": "model.safetensors",
24
+ "talker.code_predictor.lm_head.13.weight": "model.safetensors",
25
+ "talker.code_predictor.lm_head.14.biases": "model.safetensors",
26
+ "talker.code_predictor.lm_head.14.scales": "model.safetensors",
27
+ "talker.code_predictor.lm_head.14.weight": "model.safetensors",
28
+ "talker.code_predictor.lm_head.2.biases": "model.safetensors",
29
+ "talker.code_predictor.lm_head.2.scales": "model.safetensors",
30
+ "talker.code_predictor.lm_head.2.weight": "model.safetensors",
31
+ "talker.code_predictor.lm_head.3.biases": "model.safetensors",
32
+ "talker.code_predictor.lm_head.3.scales": "model.safetensors",
33
+ "talker.code_predictor.lm_head.3.weight": "model.safetensors",
34
+ "talker.code_predictor.lm_head.4.biases": "model.safetensors",
35
+ "talker.code_predictor.lm_head.4.scales": "model.safetensors",
36
+ "talker.code_predictor.lm_head.4.weight": "model.safetensors",
37
+ "talker.code_predictor.lm_head.5.biases": "model.safetensors",
38
+ "talker.code_predictor.lm_head.5.scales": "model.safetensors",
39
+ "talker.code_predictor.lm_head.5.weight": "model.safetensors",
40
+ "talker.code_predictor.lm_head.6.biases": "model.safetensors",
41
+ "talker.code_predictor.lm_head.6.scales": "model.safetensors",
42
+ "talker.code_predictor.lm_head.6.weight": "model.safetensors",
43
+ "talker.code_predictor.lm_head.7.biases": "model.safetensors",
44
+ "talker.code_predictor.lm_head.7.scales": "model.safetensors",
45
+ "talker.code_predictor.lm_head.7.weight": "model.safetensors",
46
+ "talker.code_predictor.lm_head.8.biases": "model.safetensors",
47
+ "talker.code_predictor.lm_head.8.scales": "model.safetensors",
48
+ "talker.code_predictor.lm_head.8.weight": "model.safetensors",
49
+ "talker.code_predictor.lm_head.9.biases": "model.safetensors",
50
+ "talker.code_predictor.lm_head.9.scales": "model.safetensors",
51
+ "talker.code_predictor.lm_head.9.weight": "model.safetensors",
52
+ "talker.code_predictor.model.codec_embedding.0.biases": "model.safetensors",
53
+ "talker.code_predictor.model.codec_embedding.0.scales": "model.safetensors",
54
+ "talker.code_predictor.model.codec_embedding.0.weight": "model.safetensors",
55
+ "talker.code_predictor.model.codec_embedding.1.biases": "model.safetensors",
56
+ "talker.code_predictor.model.codec_embedding.1.scales": "model.safetensors",
57
+ "talker.code_predictor.model.codec_embedding.1.weight": "model.safetensors",
58
+ "talker.code_predictor.model.codec_embedding.10.biases": "model.safetensors",
59
+ "talker.code_predictor.model.codec_embedding.10.scales": "model.safetensors",
60
+ "talker.code_predictor.model.codec_embedding.10.weight": "model.safetensors",
61
+ "talker.code_predictor.model.codec_embedding.11.biases": "model.safetensors",
62
+ "talker.code_predictor.model.codec_embedding.11.scales": "model.safetensors",
63
+ "talker.code_predictor.model.codec_embedding.11.weight": "model.safetensors",
64
+ "talker.code_predictor.model.codec_embedding.12.biases": "model.safetensors",
65
+ "talker.code_predictor.model.codec_embedding.12.scales": "model.safetensors",
66
+ "talker.code_predictor.model.codec_embedding.12.weight": "model.safetensors",
67
+ "talker.code_predictor.model.codec_embedding.13.biases": "model.safetensors",
68
+ "talker.code_predictor.model.codec_embedding.13.scales": "model.safetensors",
69
+ "talker.code_predictor.model.codec_embedding.13.weight": "model.safetensors",
70
+ "talker.code_predictor.model.codec_embedding.14.biases": "model.safetensors",
71
+ "talker.code_predictor.model.codec_embedding.14.scales": "model.safetensors",
72
+ "talker.code_predictor.model.codec_embedding.14.weight": "model.safetensors",
73
+ "talker.code_predictor.model.codec_embedding.2.biases": "model.safetensors",
74
+ "talker.code_predictor.model.codec_embedding.2.scales": "model.safetensors",
75
+ "talker.code_predictor.model.codec_embedding.2.weight": "model.safetensors",
76
+ "talker.code_predictor.model.codec_embedding.3.biases": "model.safetensors",
77
+ "talker.code_predictor.model.codec_embedding.3.scales": "model.safetensors",
78
+ "talker.code_predictor.model.codec_embedding.3.weight": "model.safetensors",
79
+ "talker.code_predictor.model.codec_embedding.4.biases": "model.safetensors",
80
+ "talker.code_predictor.model.codec_embedding.4.scales": "model.safetensors",
81
+ "talker.code_predictor.model.codec_embedding.4.weight": "model.safetensors",
82
+ "talker.code_predictor.model.codec_embedding.5.biases": "model.safetensors",
83
+ "talker.code_predictor.model.codec_embedding.5.scales": "model.safetensors",
84
+ "talker.code_predictor.model.codec_embedding.5.weight": "model.safetensors",
85
+ "talker.code_predictor.model.codec_embedding.6.biases": "model.safetensors",
86
+ "talker.code_predictor.model.codec_embedding.6.scales": "model.safetensors",
87
+ "talker.code_predictor.model.codec_embedding.6.weight": "model.safetensors",
88
+ "talker.code_predictor.model.codec_embedding.7.biases": "model.safetensors",
89
+ "talker.code_predictor.model.codec_embedding.7.scales": "model.safetensors",
90
+ "talker.code_predictor.model.codec_embedding.7.weight": "model.safetensors",
91
+ "talker.code_predictor.model.codec_embedding.8.biases": "model.safetensors",
92
+ "talker.code_predictor.model.codec_embedding.8.scales": "model.safetensors",
93
+ "talker.code_predictor.model.codec_embedding.8.weight": "model.safetensors",
94
+ "talker.code_predictor.model.codec_embedding.9.biases": "model.safetensors",
95
+ "talker.code_predictor.model.codec_embedding.9.scales": "model.safetensors",
96
+ "talker.code_predictor.model.codec_embedding.9.weight": "model.safetensors",
97
+ "talker.code_predictor.model.layers.0.input_layernorm.weight": "model.safetensors",
98
+ "talker.code_predictor.model.layers.0.mlp.down_proj.biases": "model.safetensors",
99
+ "talker.code_predictor.model.layers.0.mlp.down_proj.scales": "model.safetensors",
100
+ "talker.code_predictor.model.layers.0.mlp.down_proj.weight": "model.safetensors",
101
+ "talker.code_predictor.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
102
+ "talker.code_predictor.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
103
+ "talker.code_predictor.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
104
+ "talker.code_predictor.model.layers.0.mlp.up_proj.biases": "model.safetensors",
105
+ "talker.code_predictor.model.layers.0.mlp.up_proj.scales": "model.safetensors",
106
+ "talker.code_predictor.model.layers.0.mlp.up_proj.weight": "model.safetensors",
107
+ "talker.code_predictor.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
108
+ "talker.code_predictor.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
109
+ "talker.code_predictor.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
110
+ "talker.code_predictor.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
111
+ "talker.code_predictor.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
112
+ "talker.code_predictor.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
113
+ "talker.code_predictor.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
114
+ "talker.code_predictor.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
115
+ "talker.code_predictor.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
116
+ "talker.code_predictor.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
117
+ "talker.code_predictor.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
118
+ "talker.code_predictor.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
119
+ "talker.code_predictor.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
120
+ "talker.code_predictor.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
121
+ "talker.code_predictor.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
122
+ "talker.code_predictor.model.layers.1.input_layernorm.weight": "model.safetensors",
123
+ "talker.code_predictor.model.layers.1.mlp.down_proj.biases": "model.safetensors",
124
+ "talker.code_predictor.model.layers.1.mlp.down_proj.scales": "model.safetensors",
125
+ "talker.code_predictor.model.layers.1.mlp.down_proj.weight": "model.safetensors",
126
+ "talker.code_predictor.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
127
+ "talker.code_predictor.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
128
+ "talker.code_predictor.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
129
+ "talker.code_predictor.model.layers.1.mlp.up_proj.biases": "model.safetensors",
130
+ "talker.code_predictor.model.layers.1.mlp.up_proj.scales": "model.safetensors",
131
+ "talker.code_predictor.model.layers.1.mlp.up_proj.weight": "model.safetensors",
132
+ "talker.code_predictor.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
133
+ "talker.code_predictor.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
134
+ "talker.code_predictor.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
135
+ "talker.code_predictor.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
136
+ "talker.code_predictor.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
137
+ "talker.code_predictor.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
138
+ "talker.code_predictor.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
139
+ "talker.code_predictor.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
140
+ "talker.code_predictor.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
141
+ "talker.code_predictor.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
142
+ "talker.code_predictor.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
143
+ "talker.code_predictor.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
144
+ "talker.code_predictor.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
145
+ "talker.code_predictor.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
146
+ "talker.code_predictor.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
147
+ "talker.code_predictor.model.layers.2.input_layernorm.weight": "model.safetensors",
148
+ "talker.code_predictor.model.layers.2.mlp.down_proj.biases": "model.safetensors",
149
+ "talker.code_predictor.model.layers.2.mlp.down_proj.scales": "model.safetensors",
150
+ "talker.code_predictor.model.layers.2.mlp.down_proj.weight": "model.safetensors",
151
+ "talker.code_predictor.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
152
+ "talker.code_predictor.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
153
+ "talker.code_predictor.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
154
+ "talker.code_predictor.model.layers.2.mlp.up_proj.biases": "model.safetensors",
155
+ "talker.code_predictor.model.layers.2.mlp.up_proj.scales": "model.safetensors",
156
+ "talker.code_predictor.model.layers.2.mlp.up_proj.weight": "model.safetensors",
157
+ "talker.code_predictor.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
158
+ "talker.code_predictor.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
159
+ "talker.code_predictor.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
160
+ "talker.code_predictor.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
161
+ "talker.code_predictor.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
162
+ "talker.code_predictor.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
163
+ "talker.code_predictor.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
164
+ "talker.code_predictor.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
165
+ "talker.code_predictor.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
166
+ "talker.code_predictor.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
167
+ "talker.code_predictor.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
168
+ "talker.code_predictor.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
169
+ "talker.code_predictor.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
170
+ "talker.code_predictor.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
171
+ "talker.code_predictor.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
172
+ "talker.code_predictor.model.layers.3.input_layernorm.weight": "model.safetensors",
173
+ "talker.code_predictor.model.layers.3.mlp.down_proj.biases": "model.safetensors",
174
+ "talker.code_predictor.model.layers.3.mlp.down_proj.scales": "model.safetensors",
175
+ "talker.code_predictor.model.layers.3.mlp.down_proj.weight": "model.safetensors",
176
+ "talker.code_predictor.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
177
+ "talker.code_predictor.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
178
+ "talker.code_predictor.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
179
+ "talker.code_predictor.model.layers.3.mlp.up_proj.biases": "model.safetensors",
180
+ "talker.code_predictor.model.layers.3.mlp.up_proj.scales": "model.safetensors",
181
+ "talker.code_predictor.model.layers.3.mlp.up_proj.weight": "model.safetensors",
182
+ "talker.code_predictor.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
183
+ "talker.code_predictor.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
184
+ "talker.code_predictor.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
185
+ "talker.code_predictor.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
186
+ "talker.code_predictor.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
187
+ "talker.code_predictor.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
188
+ "talker.code_predictor.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
189
+ "talker.code_predictor.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
190
+ "talker.code_predictor.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
191
+ "talker.code_predictor.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
192
+ "talker.code_predictor.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
193
+ "talker.code_predictor.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
194
+ "talker.code_predictor.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
195
+ "talker.code_predictor.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
196
+ "talker.code_predictor.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
197
+ "talker.code_predictor.model.layers.4.input_layernorm.weight": "model.safetensors",
198
+ "talker.code_predictor.model.layers.4.mlp.down_proj.biases": "model.safetensors",
199
+ "talker.code_predictor.model.layers.4.mlp.down_proj.scales": "model.safetensors",
200
+ "talker.code_predictor.model.layers.4.mlp.down_proj.weight": "model.safetensors",
201
+ "talker.code_predictor.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
202
+ "talker.code_predictor.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
203
+ "talker.code_predictor.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
204
+ "talker.code_predictor.model.layers.4.mlp.up_proj.biases": "model.safetensors",
205
+ "talker.code_predictor.model.layers.4.mlp.up_proj.scales": "model.safetensors",
206
+ "talker.code_predictor.model.layers.4.mlp.up_proj.weight": "model.safetensors",
207
+ "talker.code_predictor.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
208
+ "talker.code_predictor.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
209
+ "talker.code_predictor.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
210
+ "talker.code_predictor.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
211
+ "talker.code_predictor.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
212
+ "talker.code_predictor.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
213
+ "talker.code_predictor.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
214
+ "talker.code_predictor.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
215
+ "talker.code_predictor.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
216
+ "talker.code_predictor.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
217
+ "talker.code_predictor.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
218
+ "talker.code_predictor.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
219
+ "talker.code_predictor.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
220
+ "talker.code_predictor.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
221
+ "talker.code_predictor.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
222
+ "talker.code_predictor.model.norm.weight": "model.safetensors",
223
+ "talker.code_predictor.small_to_mtp_projection.bias": "model.safetensors",
224
+ "talker.code_predictor.small_to_mtp_projection.biases": "model.safetensors",
225
+ "talker.code_predictor.small_to_mtp_projection.scales": "model.safetensors",
226
+ "talker.code_predictor.small_to_mtp_projection.weight": "model.safetensors",
227
+ "talker.codec_head.biases": "model.safetensors",
228
+ "talker.codec_head.scales": "model.safetensors",
229
+ "talker.codec_head.weight": "model.safetensors",
230
+ "talker.model.codec_embedding.biases": "model.safetensors",
231
+ "talker.model.codec_embedding.scales": "model.safetensors",
232
+ "talker.model.codec_embedding.weight": "model.safetensors",
233
+ "talker.model.layers.0.input_layernorm.weight": "model.safetensors",
234
+ "talker.model.layers.0.mlp.down_proj.biases": "model.safetensors",
235
+ "talker.model.layers.0.mlp.down_proj.scales": "model.safetensors",
236
+ "talker.model.layers.0.mlp.down_proj.weight": "model.safetensors",
237
+ "talker.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
238
+ "talker.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
239
+ "talker.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
240
+ "talker.model.layers.0.mlp.up_proj.biases": "model.safetensors",
241
+ "talker.model.layers.0.mlp.up_proj.scales": "model.safetensors",
242
+ "talker.model.layers.0.mlp.up_proj.weight": "model.safetensors",
243
+ "talker.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
244
+ "talker.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
245
+ "talker.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
246
+ "talker.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
247
+ "talker.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
248
+ "talker.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
249
+ "talker.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
250
+ "talker.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
251
+ "talker.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
252
+ "talker.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
253
+ "talker.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
254
+ "talker.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
255
+ "talker.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
256
+ "talker.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
257
+ "talker.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
258
+ "talker.model.layers.1.input_layernorm.weight": "model.safetensors",
259
+ "talker.model.layers.1.mlp.down_proj.biases": "model.safetensors",
260
+ "talker.model.layers.1.mlp.down_proj.scales": "model.safetensors",
261
+ "talker.model.layers.1.mlp.down_proj.weight": "model.safetensors",
262
+ "talker.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
263
+ "talker.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
264
+ "talker.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
265
+ "talker.model.layers.1.mlp.up_proj.biases": "model.safetensors",
266
+ "talker.model.layers.1.mlp.up_proj.scales": "model.safetensors",
267
+ "talker.model.layers.1.mlp.up_proj.weight": "model.safetensors",
268
+ "talker.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
269
+ "talker.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
270
+ "talker.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
271
+ "talker.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
272
+ "talker.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
273
+ "talker.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
274
+ "talker.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
275
+ "talker.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
276
+ "talker.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
277
+ "talker.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
278
+ "talker.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
279
+ "talker.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
280
+ "talker.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
281
+ "talker.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
282
+ "talker.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
283
+ "talker.model.layers.10.input_layernorm.weight": "model.safetensors",
284
+ "talker.model.layers.10.mlp.down_proj.biases": "model.safetensors",
285
+ "talker.model.layers.10.mlp.down_proj.scales": "model.safetensors",
286
+ "talker.model.layers.10.mlp.down_proj.weight": "model.safetensors",
287
+ "talker.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
288
+ "talker.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
289
+ "talker.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
290
+ "talker.model.layers.10.mlp.up_proj.biases": "model.safetensors",
291
+ "talker.model.layers.10.mlp.up_proj.scales": "model.safetensors",
292
+ "talker.model.layers.10.mlp.up_proj.weight": "model.safetensors",
293
+ "talker.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
294
+ "talker.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
295
+ "talker.model.layers.10.self_attn.k_proj.biases": "model.safetensors",
296
+ "talker.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
297
+ "talker.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
298
+ "talker.model.layers.10.self_attn.o_proj.biases": "model.safetensors",
299
+ "talker.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
300
+ "talker.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
301
+ "talker.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
302
+ "talker.model.layers.10.self_attn.q_proj.biases": "model.safetensors",
303
+ "talker.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
304
+ "talker.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
305
+ "talker.model.layers.10.self_attn.v_proj.biases": "model.safetensors",
306
+ "talker.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
307
+ "talker.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
308
+ "talker.model.layers.11.input_layernorm.weight": "model.safetensors",
309
+ "talker.model.layers.11.mlp.down_proj.biases": "model.safetensors",
310
+ "talker.model.layers.11.mlp.down_proj.scales": "model.safetensors",
311
+ "talker.model.layers.11.mlp.down_proj.weight": "model.safetensors",
312
+ "talker.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
313
+ "talker.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
314
+ "talker.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
315
+ "talker.model.layers.11.mlp.up_proj.biases": "model.safetensors",
316
+ "talker.model.layers.11.mlp.up_proj.scales": "model.safetensors",
317
+ "talker.model.layers.11.mlp.up_proj.weight": "model.safetensors",
318
+ "talker.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
319
+ "talker.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
320
+ "talker.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
321
+ "talker.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
322
+ "talker.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
323
+ "talker.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
324
+ "talker.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
325
+ "talker.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
326
+ "talker.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
327
+ "talker.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
328
+ "talker.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
329
+ "talker.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
330
+ "talker.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
331
+ "talker.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
332
+ "talker.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
333
+ "talker.model.layers.12.input_layernorm.weight": "model.safetensors",
334
+ "talker.model.layers.12.mlp.down_proj.biases": "model.safetensors",
335
+ "talker.model.layers.12.mlp.down_proj.scales": "model.safetensors",
336
+ "talker.model.layers.12.mlp.down_proj.weight": "model.safetensors",
337
+ "talker.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
338
+ "talker.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
339
+ "talker.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
340
+ "talker.model.layers.12.mlp.up_proj.biases": "model.safetensors",
341
+ "talker.model.layers.12.mlp.up_proj.scales": "model.safetensors",
342
+ "talker.model.layers.12.mlp.up_proj.weight": "model.safetensors",
343
+ "talker.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
344
+ "talker.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
345
+ "talker.model.layers.12.self_attn.k_proj.biases": "model.safetensors",
346
+ "talker.model.layers.12.self_attn.k_proj.scales": "model.safetensors",
347
+ "talker.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
348
+ "talker.model.layers.12.self_attn.o_proj.biases": "model.safetensors",
349
+ "talker.model.layers.12.self_attn.o_proj.scales": "model.safetensors",
350
+ "talker.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
351
+ "talker.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
352
+ "talker.model.layers.12.self_attn.q_proj.biases": "model.safetensors",
353
+ "talker.model.layers.12.self_attn.q_proj.scales": "model.safetensors",
354
+ "talker.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
355
+ "talker.model.layers.12.self_attn.v_proj.biases": "model.safetensors",
356
+ "talker.model.layers.12.self_attn.v_proj.scales": "model.safetensors",
357
+ "talker.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
358
+ "talker.model.layers.13.input_layernorm.weight": "model.safetensors",
359
+ "talker.model.layers.13.mlp.down_proj.biases": "model.safetensors",
360
+ "talker.model.layers.13.mlp.down_proj.scales": "model.safetensors",
361
+ "talker.model.layers.13.mlp.down_proj.weight": "model.safetensors",
362
+ "talker.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
363
+ "talker.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
364
+ "talker.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
365
+ "talker.model.layers.13.mlp.up_proj.biases": "model.safetensors",
366
+ "talker.model.layers.13.mlp.up_proj.scales": "model.safetensors",
367
+ "talker.model.layers.13.mlp.up_proj.weight": "model.safetensors",
368
+ "talker.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
369
+ "talker.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
370
+ "talker.model.layers.13.self_attn.k_proj.biases": "model.safetensors",
371
+ "talker.model.layers.13.self_attn.k_proj.scales": "model.safetensors",
372
+ "talker.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
373
+ "talker.model.layers.13.self_attn.o_proj.biases": "model.safetensors",
374
+ "talker.model.layers.13.self_attn.o_proj.scales": "model.safetensors",
375
+ "talker.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
376
+ "talker.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
377
+ "talker.model.layers.13.self_attn.q_proj.biases": "model.safetensors",
378
+ "talker.model.layers.13.self_attn.q_proj.scales": "model.safetensors",
379
+ "talker.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
380
+ "talker.model.layers.13.self_attn.v_proj.biases": "model.safetensors",
381
+ "talker.model.layers.13.self_attn.v_proj.scales": "model.safetensors",
382
+ "talker.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
383
+ "talker.model.layers.14.input_layernorm.weight": "model.safetensors",
384
+ "talker.model.layers.14.mlp.down_proj.biases": "model.safetensors",
385
+ "talker.model.layers.14.mlp.down_proj.scales": "model.safetensors",
386
+ "talker.model.layers.14.mlp.down_proj.weight": "model.safetensors",
387
+ "talker.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
388
+ "talker.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
389
+ "talker.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
390
+ "talker.model.layers.14.mlp.up_proj.biases": "model.safetensors",
391
+ "talker.model.layers.14.mlp.up_proj.scales": "model.safetensors",
392
+ "talker.model.layers.14.mlp.up_proj.weight": "model.safetensors",
393
+ "talker.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
394
+ "talker.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
395
+ "talker.model.layers.14.self_attn.k_proj.biases": "model.safetensors",
396
+ "talker.model.layers.14.self_attn.k_proj.scales": "model.safetensors",
397
+ "talker.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
398
+ "talker.model.layers.14.self_attn.o_proj.biases": "model.safetensors",
399
+ "talker.model.layers.14.self_attn.o_proj.scales": "model.safetensors",
400
+ "talker.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
401
+ "talker.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
402
+ "talker.model.layers.14.self_attn.q_proj.biases": "model.safetensors",
403
+ "talker.model.layers.14.self_attn.q_proj.scales": "model.safetensors",
404
+ "talker.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
405
+ "talker.model.layers.14.self_attn.v_proj.biases": "model.safetensors",
406
+ "talker.model.layers.14.self_attn.v_proj.scales": "model.safetensors",
407
+ "talker.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
408
+ "talker.model.layers.15.input_layernorm.weight": "model.safetensors",
409
+ "talker.model.layers.15.mlp.down_proj.biases": "model.safetensors",
410
+ "talker.model.layers.15.mlp.down_proj.scales": "model.safetensors",
411
+ "talker.model.layers.15.mlp.down_proj.weight": "model.safetensors",
412
+ "talker.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
413
+ "talker.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
414
+ "talker.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
415
+ "talker.model.layers.15.mlp.up_proj.biases": "model.safetensors",
416
+ "talker.model.layers.15.mlp.up_proj.scales": "model.safetensors",
417
+ "talker.model.layers.15.mlp.up_proj.weight": "model.safetensors",
418
+ "talker.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
419
+ "talker.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
420
+ "talker.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
421
+ "talker.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
422
+ "talker.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
423
+ "talker.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
424
+ "talker.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
425
+ "talker.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
426
+ "talker.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
427
+ "talker.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
428
+ "talker.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
429
+ "talker.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
430
+ "talker.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
431
+ "talker.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
432
+ "talker.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
433
+ "talker.model.layers.16.input_layernorm.weight": "model.safetensors",
434
+ "talker.model.layers.16.mlp.down_proj.biases": "model.safetensors",
435
+ "talker.model.layers.16.mlp.down_proj.scales": "model.safetensors",
436
+ "talker.model.layers.16.mlp.down_proj.weight": "model.safetensors",
437
+ "talker.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
438
+ "talker.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
439
+ "talker.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
440
+ "talker.model.layers.16.mlp.up_proj.biases": "model.safetensors",
441
+ "talker.model.layers.16.mlp.up_proj.scales": "model.safetensors",
442
+ "talker.model.layers.16.mlp.up_proj.weight": "model.safetensors",
443
+ "talker.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
444
+ "talker.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
445
+ "talker.model.layers.16.self_attn.k_proj.biases": "model.safetensors",
446
+ "talker.model.layers.16.self_attn.k_proj.scales": "model.safetensors",
447
+ "talker.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
448
+ "talker.model.layers.16.self_attn.o_proj.biases": "model.safetensors",
449
+ "talker.model.layers.16.self_attn.o_proj.scales": "model.safetensors",
450
+ "talker.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
451
+ "talker.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
452
+ "talker.model.layers.16.self_attn.q_proj.biases": "model.safetensors",
453
+ "talker.model.layers.16.self_attn.q_proj.scales": "model.safetensors",
454
+ "talker.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
455
+ "talker.model.layers.16.self_attn.v_proj.biases": "model.safetensors",
456
+ "talker.model.layers.16.self_attn.v_proj.scales": "model.safetensors",
457
+ "talker.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
458
+ "talker.model.layers.17.input_layernorm.weight": "model.safetensors",
459
+ "talker.model.layers.17.mlp.down_proj.biases": "model.safetensors",
460
+ "talker.model.layers.17.mlp.down_proj.scales": "model.safetensors",
461
+ "talker.model.layers.17.mlp.down_proj.weight": "model.safetensors",
462
+ "talker.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
463
+ "talker.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
464
+ "talker.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
465
+ "talker.model.layers.17.mlp.up_proj.biases": "model.safetensors",
466
+ "talker.model.layers.17.mlp.up_proj.scales": "model.safetensors",
467
+ "talker.model.layers.17.mlp.up_proj.weight": "model.safetensors",
468
+ "talker.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
469
+ "talker.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
470
+ "talker.model.layers.17.self_attn.k_proj.biases": "model.safetensors",
471
+ "talker.model.layers.17.self_attn.k_proj.scales": "model.safetensors",
472
+ "talker.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
473
+ "talker.model.layers.17.self_attn.o_proj.biases": "model.safetensors",
474
+ "talker.model.layers.17.self_attn.o_proj.scales": "model.safetensors",
475
+ "talker.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
476
+ "talker.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
477
+ "talker.model.layers.17.self_attn.q_proj.biases": "model.safetensors",
478
+ "talker.model.layers.17.self_attn.q_proj.scales": "model.safetensors",
479
+ "talker.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
480
+ "talker.model.layers.17.self_attn.v_proj.biases": "model.safetensors",
481
+ "talker.model.layers.17.self_attn.v_proj.scales": "model.safetensors",
482
+ "talker.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
483
+ "talker.model.layers.18.input_layernorm.weight": "model.safetensors",
484
+ "talker.model.layers.18.mlp.down_proj.biases": "model.safetensors",
485
+ "talker.model.layers.18.mlp.down_proj.scales": "model.safetensors",
486
+ "talker.model.layers.18.mlp.down_proj.weight": "model.safetensors",
487
+ "talker.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
488
+ "talker.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
489
+ "talker.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
490
+ "talker.model.layers.18.mlp.up_proj.biases": "model.safetensors",
491
+ "talker.model.layers.18.mlp.up_proj.scales": "model.safetensors",
492
+ "talker.model.layers.18.mlp.up_proj.weight": "model.safetensors",
493
+ "talker.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
494
+ "talker.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
495
+ "talker.model.layers.18.self_attn.k_proj.biases": "model.safetensors",
496
+ "talker.model.layers.18.self_attn.k_proj.scales": "model.safetensors",
497
+ "talker.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
498
+ "talker.model.layers.18.self_attn.o_proj.biases": "model.safetensors",
499
+ "talker.model.layers.18.self_attn.o_proj.scales": "model.safetensors",
500
+ "talker.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
501
+ "talker.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
502
+ "talker.model.layers.18.self_attn.q_proj.biases": "model.safetensors",
503
+ "talker.model.layers.18.self_attn.q_proj.scales": "model.safetensors",
504
+ "talker.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
505
+ "talker.model.layers.18.self_attn.v_proj.biases": "model.safetensors",
506
+ "talker.model.layers.18.self_attn.v_proj.scales": "model.safetensors",
507
+ "talker.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
508
+ "talker.model.layers.19.input_layernorm.weight": "model.safetensors",
509
+ "talker.model.layers.19.mlp.down_proj.biases": "model.safetensors",
510
+ "talker.model.layers.19.mlp.down_proj.scales": "model.safetensors",
511
+ "talker.model.layers.19.mlp.down_proj.weight": "model.safetensors",
512
+ "talker.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
513
+ "talker.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
514
+ "talker.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
515
+ "talker.model.layers.19.mlp.up_proj.biases": "model.safetensors",
516
+ "talker.model.layers.19.mlp.up_proj.scales": "model.safetensors",
517
+ "talker.model.layers.19.mlp.up_proj.weight": "model.safetensors",
518
+ "talker.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
519
+ "talker.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
520
+ "talker.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
521
+ "talker.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
522
+ "talker.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
523
+ "talker.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
524
+ "talker.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
525
+ "talker.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
526
+ "talker.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
527
+ "talker.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
528
+ "talker.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
529
+ "talker.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
530
+ "talker.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
531
+ "talker.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
532
+ "talker.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
533
+ "talker.model.layers.2.input_layernorm.weight": "model.safetensors",
534
+ "talker.model.layers.2.mlp.down_proj.biases": "model.safetensors",
535
+ "talker.model.layers.2.mlp.down_proj.scales": "model.safetensors",
536
+ "talker.model.layers.2.mlp.down_proj.weight": "model.safetensors",
537
+ "talker.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
538
+ "talker.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
539
+ "talker.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
540
+ "talker.model.layers.2.mlp.up_proj.biases": "model.safetensors",
541
+ "talker.model.layers.2.mlp.up_proj.scales": "model.safetensors",
542
+ "talker.model.layers.2.mlp.up_proj.weight": "model.safetensors",
543
+ "talker.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
544
+ "talker.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
545
+ "talker.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
546
+ "talker.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
547
+ "talker.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
548
+ "talker.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
549
+ "talker.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
550
+ "talker.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
551
+ "talker.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
552
+ "talker.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
553
+ "talker.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
554
+ "talker.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
555
+ "talker.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
556
+ "talker.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
557
+ "talker.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
558
+ "talker.model.layers.20.input_layernorm.weight": "model.safetensors",
559
+ "talker.model.layers.20.mlp.down_proj.biases": "model.safetensors",
560
+ "talker.model.layers.20.mlp.down_proj.scales": "model.safetensors",
561
+ "talker.model.layers.20.mlp.down_proj.weight": "model.safetensors",
562
+ "talker.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
563
+ "talker.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
564
+ "talker.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
565
+ "talker.model.layers.20.mlp.up_proj.biases": "model.safetensors",
566
+ "talker.model.layers.20.mlp.up_proj.scales": "model.safetensors",
567
+ "talker.model.layers.20.mlp.up_proj.weight": "model.safetensors",
568
+ "talker.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
569
+ "talker.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
570
+ "talker.model.layers.20.self_attn.k_proj.biases": "model.safetensors",
571
+ "talker.model.layers.20.self_attn.k_proj.scales": "model.safetensors",
572
+ "talker.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
573
+ "talker.model.layers.20.self_attn.o_proj.biases": "model.safetensors",
574
+ "talker.model.layers.20.self_attn.o_proj.scales": "model.safetensors",
575
+ "talker.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
576
+ "talker.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
577
+ "talker.model.layers.20.self_attn.q_proj.biases": "model.safetensors",
578
+ "talker.model.layers.20.self_attn.q_proj.scales": "model.safetensors",
579
+ "talker.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
580
+ "talker.model.layers.20.self_attn.v_proj.biases": "model.safetensors",
581
+ "talker.model.layers.20.self_attn.v_proj.scales": "model.safetensors",
582
+ "talker.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
583
+ "talker.model.layers.21.input_layernorm.weight": "model.safetensors",
584
+ "talker.model.layers.21.mlp.down_proj.biases": "model.safetensors",
585
+ "talker.model.layers.21.mlp.down_proj.scales": "model.safetensors",
586
+ "talker.model.layers.21.mlp.down_proj.weight": "model.safetensors",
587
+ "talker.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
588
+ "talker.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
589
+ "talker.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
590
+ "talker.model.layers.21.mlp.up_proj.biases": "model.safetensors",
591
+ "talker.model.layers.21.mlp.up_proj.scales": "model.safetensors",
592
+ "talker.model.layers.21.mlp.up_proj.weight": "model.safetensors",
593
+ "talker.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
594
+ "talker.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
595
+ "talker.model.layers.21.self_attn.k_proj.biases": "model.safetensors",
596
+ "talker.model.layers.21.self_attn.k_proj.scales": "model.safetensors",
597
+ "talker.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
598
+ "talker.model.layers.21.self_attn.o_proj.biases": "model.safetensors",
599
+ "talker.model.layers.21.self_attn.o_proj.scales": "model.safetensors",
600
+ "talker.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
601
+ "talker.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
602
+ "talker.model.layers.21.self_attn.q_proj.biases": "model.safetensors",
603
+ "talker.model.layers.21.self_attn.q_proj.scales": "model.safetensors",
604
+ "talker.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
605
+ "talker.model.layers.21.self_attn.v_proj.biases": "model.safetensors",
606
+ "talker.model.layers.21.self_attn.v_proj.scales": "model.safetensors",
607
+ "talker.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
608
+ "talker.model.layers.22.input_layernorm.weight": "model.safetensors",
609
+ "talker.model.layers.22.mlp.down_proj.biases": "model.safetensors",
610
+ "talker.model.layers.22.mlp.down_proj.scales": "model.safetensors",
611
+ "talker.model.layers.22.mlp.down_proj.weight": "model.safetensors",
612
+ "talker.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
613
+ "talker.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
614
+ "talker.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
615
+ "talker.model.layers.22.mlp.up_proj.biases": "model.safetensors",
616
+ "talker.model.layers.22.mlp.up_proj.scales": "model.safetensors",
617
+ "talker.model.layers.22.mlp.up_proj.weight": "model.safetensors",
618
+ "talker.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
619
+ "talker.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
620
+ "talker.model.layers.22.self_attn.k_proj.biases": "model.safetensors",
621
+ "talker.model.layers.22.self_attn.k_proj.scales": "model.safetensors",
622
+ "talker.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
623
+ "talker.model.layers.22.self_attn.o_proj.biases": "model.safetensors",
624
+ "talker.model.layers.22.self_attn.o_proj.scales": "model.safetensors",
625
+ "talker.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
626
+ "talker.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
627
+ "talker.model.layers.22.self_attn.q_proj.biases": "model.safetensors",
628
+ "talker.model.layers.22.self_attn.q_proj.scales": "model.safetensors",
629
+ "talker.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
630
+ "talker.model.layers.22.self_attn.v_proj.biases": "model.safetensors",
631
+ "talker.model.layers.22.self_attn.v_proj.scales": "model.safetensors",
632
+ "talker.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
633
+ "talker.model.layers.23.input_layernorm.weight": "model.safetensors",
634
+ "talker.model.layers.23.mlp.down_proj.biases": "model.safetensors",
635
+ "talker.model.layers.23.mlp.down_proj.scales": "model.safetensors",
636
+ "talker.model.layers.23.mlp.down_proj.weight": "model.safetensors",
637
+ "talker.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
638
+ "talker.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
639
+ "talker.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
640
+ "talker.model.layers.23.mlp.up_proj.biases": "model.safetensors",
641
+ "talker.model.layers.23.mlp.up_proj.scales": "model.safetensors",
642
+ "talker.model.layers.23.mlp.up_proj.weight": "model.safetensors",
643
+ "talker.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
644
+ "talker.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
645
+ "talker.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
646
+ "talker.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
647
+ "talker.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
648
+ "talker.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
649
+ "talker.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
650
+ "talker.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
651
+ "talker.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
652
+ "talker.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
653
+ "talker.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
654
+ "talker.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
655
+ "talker.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
656
+ "talker.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
657
+ "talker.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
658
+ "talker.model.layers.24.input_layernorm.weight": "model.safetensors",
659
+ "talker.model.layers.24.mlp.down_proj.biases": "model.safetensors",
660
+ "talker.model.layers.24.mlp.down_proj.scales": "model.safetensors",
661
+ "talker.model.layers.24.mlp.down_proj.weight": "model.safetensors",
662
+ "talker.model.layers.24.mlp.gate_proj.biases": "model.safetensors",
663
+ "talker.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
664
+ "talker.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
665
+ "talker.model.layers.24.mlp.up_proj.biases": "model.safetensors",
666
+ "talker.model.layers.24.mlp.up_proj.scales": "model.safetensors",
667
+ "talker.model.layers.24.mlp.up_proj.weight": "model.safetensors",
668
+ "talker.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
669
+ "talker.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
670
+ "talker.model.layers.24.self_attn.k_proj.biases": "model.safetensors",
671
+ "talker.model.layers.24.self_attn.k_proj.scales": "model.safetensors",
672
+ "talker.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
673
+ "talker.model.layers.24.self_attn.o_proj.biases": "model.safetensors",
674
+ "talker.model.layers.24.self_attn.o_proj.scales": "model.safetensors",
675
+ "talker.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
676
+ "talker.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
677
+ "talker.model.layers.24.self_attn.q_proj.biases": "model.safetensors",
678
+ "talker.model.layers.24.self_attn.q_proj.scales": "model.safetensors",
679
+ "talker.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
680
+ "talker.model.layers.24.self_attn.v_proj.biases": "model.safetensors",
681
+ "talker.model.layers.24.self_attn.v_proj.scales": "model.safetensors",
682
+ "talker.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
683
+ "talker.model.layers.25.input_layernorm.weight": "model.safetensors",
684
+ "talker.model.layers.25.mlp.down_proj.biases": "model.safetensors",
685
+ "talker.model.layers.25.mlp.down_proj.scales": "model.safetensors",
686
+ "talker.model.layers.25.mlp.down_proj.weight": "model.safetensors",
687
+ "talker.model.layers.25.mlp.gate_proj.biases": "model.safetensors",
688
+ "talker.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
689
+ "talker.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
690
+ "talker.model.layers.25.mlp.up_proj.biases": "model.safetensors",
691
+ "talker.model.layers.25.mlp.up_proj.scales": "model.safetensors",
692
+ "talker.model.layers.25.mlp.up_proj.weight": "model.safetensors",
693
+ "talker.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
694
+ "talker.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
695
+ "talker.model.layers.25.self_attn.k_proj.biases": "model.safetensors",
696
+ "talker.model.layers.25.self_attn.k_proj.scales": "model.safetensors",
697
+ "talker.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
698
+ "talker.model.layers.25.self_attn.o_proj.biases": "model.safetensors",
699
+ "talker.model.layers.25.self_attn.o_proj.scales": "model.safetensors",
700
+ "talker.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
701
+ "talker.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
702
+ "talker.model.layers.25.self_attn.q_proj.biases": "model.safetensors",
703
+ "talker.model.layers.25.self_attn.q_proj.scales": "model.safetensors",
704
+ "talker.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
705
+ "talker.model.layers.25.self_attn.v_proj.biases": "model.safetensors",
706
+ "talker.model.layers.25.self_attn.v_proj.scales": "model.safetensors",
707
+ "talker.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
708
+ "talker.model.layers.26.input_layernorm.weight": "model.safetensors",
709
+ "talker.model.layers.26.mlp.down_proj.biases": "model.safetensors",
710
+ "talker.model.layers.26.mlp.down_proj.scales": "model.safetensors",
711
+ "talker.model.layers.26.mlp.down_proj.weight": "model.safetensors",
712
+ "talker.model.layers.26.mlp.gate_proj.biases": "model.safetensors",
713
+ "talker.model.layers.26.mlp.gate_proj.scales": "model.safetensors",
714
+ "talker.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
715
+ "talker.model.layers.26.mlp.up_proj.biases": "model.safetensors",
716
+ "talker.model.layers.26.mlp.up_proj.scales": "model.safetensors",
717
+ "talker.model.layers.26.mlp.up_proj.weight": "model.safetensors",
718
+ "talker.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
719
+ "talker.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
720
+ "talker.model.layers.26.self_attn.k_proj.biases": "model.safetensors",
721
+ "talker.model.layers.26.self_attn.k_proj.scales": "model.safetensors",
722
+ "talker.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
723
+ "talker.model.layers.26.self_attn.o_proj.biases": "model.safetensors",
724
+ "talker.model.layers.26.self_attn.o_proj.scales": "model.safetensors",
725
+ "talker.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
726
+ "talker.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
727
+ "talker.model.layers.26.self_attn.q_proj.biases": "model.safetensors",
728
+ "talker.model.layers.26.self_attn.q_proj.scales": "model.safetensors",
729
+ "talker.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
730
+ "talker.model.layers.26.self_attn.v_proj.biases": "model.safetensors",
731
+ "talker.model.layers.26.self_attn.v_proj.scales": "model.safetensors",
732
+ "talker.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
733
+ "talker.model.layers.27.input_layernorm.weight": "model.safetensors",
734
+ "talker.model.layers.27.mlp.down_proj.biases": "model.safetensors",
735
+ "talker.model.layers.27.mlp.down_proj.scales": "model.safetensors",
736
+ "talker.model.layers.27.mlp.down_proj.weight": "model.safetensors",
737
+ "talker.model.layers.27.mlp.gate_proj.biases": "model.safetensors",
738
+ "talker.model.layers.27.mlp.gate_proj.scales": "model.safetensors",
739
+ "talker.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
740
+ "talker.model.layers.27.mlp.up_proj.biases": "model.safetensors",
741
+ "talker.model.layers.27.mlp.up_proj.scales": "model.safetensors",
742
+ "talker.model.layers.27.mlp.up_proj.weight": "model.safetensors",
743
+ "talker.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
744
+ "talker.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
745
+ "talker.model.layers.27.self_attn.k_proj.biases": "model.safetensors",
746
+ "talker.model.layers.27.self_attn.k_proj.scales": "model.safetensors",
747
+ "talker.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
748
+ "talker.model.layers.27.self_attn.o_proj.biases": "model.safetensors",
749
+ "talker.model.layers.27.self_attn.o_proj.scales": "model.safetensors",
750
+ "talker.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
751
+ "talker.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
752
+ "talker.model.layers.27.self_attn.q_proj.biases": "model.safetensors",
753
+ "talker.model.layers.27.self_attn.q_proj.scales": "model.safetensors",
754
+ "talker.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
755
+ "talker.model.layers.27.self_attn.v_proj.biases": "model.safetensors",
756
+ "talker.model.layers.27.self_attn.v_proj.scales": "model.safetensors",
757
+ "talker.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
758
+ "talker.model.layers.3.input_layernorm.weight": "model.safetensors",
759
+ "talker.model.layers.3.mlp.down_proj.biases": "model.safetensors",
760
+ "talker.model.layers.3.mlp.down_proj.scales": "model.safetensors",
761
+ "talker.model.layers.3.mlp.down_proj.weight": "model.safetensors",
762
+ "talker.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
763
+ "talker.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
764
+ "talker.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
765
+ "talker.model.layers.3.mlp.up_proj.biases": "model.safetensors",
766
+ "talker.model.layers.3.mlp.up_proj.scales": "model.safetensors",
767
+ "talker.model.layers.3.mlp.up_proj.weight": "model.safetensors",
768
+ "talker.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
769
+ "talker.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
770
+ "talker.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
771
+ "talker.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
772
+ "talker.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
773
+ "talker.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
774
+ "talker.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
775
+ "talker.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
776
+ "talker.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
777
+ "talker.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
778
+ "talker.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
779
+ "talker.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
780
+ "talker.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
781
+ "talker.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
782
+ "talker.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
783
+ "talker.model.layers.4.input_layernorm.weight": "model.safetensors",
784
+ "talker.model.layers.4.mlp.down_proj.biases": "model.safetensors",
785
+ "talker.model.layers.4.mlp.down_proj.scales": "model.safetensors",
786
+ "talker.model.layers.4.mlp.down_proj.weight": "model.safetensors",
787
+ "talker.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
788
+ "talker.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
789
+ "talker.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
790
+ "talker.model.layers.4.mlp.up_proj.biases": "model.safetensors",
791
+ "talker.model.layers.4.mlp.up_proj.scales": "model.safetensors",
792
+ "talker.model.layers.4.mlp.up_proj.weight": "model.safetensors",
793
+ "talker.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
794
+ "talker.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
795
+ "talker.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
796
+ "talker.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
797
+ "talker.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
798
+ "talker.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
799
+ "talker.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
800
+ "talker.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
801
+ "talker.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
802
+ "talker.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
803
+ "talker.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
804
+ "talker.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
805
+ "talker.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
806
+ "talker.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
807
+ "talker.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
808
+ "talker.model.layers.5.input_layernorm.weight": "model.safetensors",
809
+ "talker.model.layers.5.mlp.down_proj.biases": "model.safetensors",
810
+ "talker.model.layers.5.mlp.down_proj.scales": "model.safetensors",
811
+ "talker.model.layers.5.mlp.down_proj.weight": "model.safetensors",
812
+ "talker.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
813
+ "talker.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
814
+ "talker.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
815
+ "talker.model.layers.5.mlp.up_proj.biases": "model.safetensors",
816
+ "talker.model.layers.5.mlp.up_proj.scales": "model.safetensors",
817
+ "talker.model.layers.5.mlp.up_proj.weight": "model.safetensors",
818
+ "talker.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
819
+ "talker.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
820
+ "talker.model.layers.5.self_attn.k_proj.biases": "model.safetensors",
821
+ "talker.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
822
+ "talker.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
823
+ "talker.model.layers.5.self_attn.o_proj.biases": "model.safetensors",
824
+ "talker.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
825
+ "talker.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
826
+ "talker.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
827
+ "talker.model.layers.5.self_attn.q_proj.biases": "model.safetensors",
828
+ "talker.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
829
+ "talker.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
830
+ "talker.model.layers.5.self_attn.v_proj.biases": "model.safetensors",
831
+ "talker.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
832
+ "talker.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
833
+ "talker.model.layers.6.input_layernorm.weight": "model.safetensors",
834
+ "talker.model.layers.6.mlp.down_proj.biases": "model.safetensors",
835
+ "talker.model.layers.6.mlp.down_proj.scales": "model.safetensors",
836
+ "talker.model.layers.6.mlp.down_proj.weight": "model.safetensors",
837
+ "talker.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
838
+ "talker.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
839
+ "talker.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
840
+ "talker.model.layers.6.mlp.up_proj.biases": "model.safetensors",
841
+ "talker.model.layers.6.mlp.up_proj.scales": "model.safetensors",
842
+ "talker.model.layers.6.mlp.up_proj.weight": "model.safetensors",
843
+ "talker.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
844
+ "talker.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
845
+ "talker.model.layers.6.self_attn.k_proj.biases": "model.safetensors",
846
+ "talker.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
847
+ "talker.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
848
+ "talker.model.layers.6.self_attn.o_proj.biases": "model.safetensors",
849
+ "talker.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
850
+ "talker.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
851
+ "talker.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
852
+ "talker.model.layers.6.self_attn.q_proj.biases": "model.safetensors",
853
+ "talker.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
854
+ "talker.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
855
+ "talker.model.layers.6.self_attn.v_proj.biases": "model.safetensors",
856
+ "talker.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
857
+ "talker.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
858
+ "talker.model.layers.7.input_layernorm.weight": "model.safetensors",
859
+ "talker.model.layers.7.mlp.down_proj.biases": "model.safetensors",
860
+ "talker.model.layers.7.mlp.down_proj.scales": "model.safetensors",
861
+ "talker.model.layers.7.mlp.down_proj.weight": "model.safetensors",
862
+ "talker.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
863
+ "talker.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
864
+ "talker.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
865
+ "talker.model.layers.7.mlp.up_proj.biases": "model.safetensors",
866
+ "talker.model.layers.7.mlp.up_proj.scales": "model.safetensors",
867
+ "talker.model.layers.7.mlp.up_proj.weight": "model.safetensors",
868
+ "talker.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
869
+ "talker.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
870
+ "talker.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
871
+ "talker.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
872
+ "talker.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
873
+ "talker.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
874
+ "talker.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
875
+ "talker.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
876
+ "talker.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
877
+ "talker.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
878
+ "talker.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
879
+ "talker.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
880
+ "talker.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
881
+ "talker.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
882
+ "talker.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
883
+ "talker.model.layers.8.input_layernorm.weight": "model.safetensors",
884
+ "talker.model.layers.8.mlp.down_proj.biases": "model.safetensors",
885
+ "talker.model.layers.8.mlp.down_proj.scales": "model.safetensors",
886
+ "talker.model.layers.8.mlp.down_proj.weight": "model.safetensors",
887
+ "talker.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
888
+ "talker.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
889
+ "talker.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
890
+ "talker.model.layers.8.mlp.up_proj.biases": "model.safetensors",
891
+ "talker.model.layers.8.mlp.up_proj.scales": "model.safetensors",
892
+ "talker.model.layers.8.mlp.up_proj.weight": "model.safetensors",
893
+ "talker.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
894
+ "talker.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
895
+ "talker.model.layers.8.self_attn.k_proj.biases": "model.safetensors",
896
+ "talker.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
897
+ "talker.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
898
+ "talker.model.layers.8.self_attn.o_proj.biases": "model.safetensors",
899
+ "talker.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
900
+ "talker.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
901
+ "talker.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
902
+ "talker.model.layers.8.self_attn.q_proj.biases": "model.safetensors",
903
+ "talker.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
904
+ "talker.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
905
+ "talker.model.layers.8.self_attn.v_proj.biases": "model.safetensors",
906
+ "talker.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
907
+ "talker.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
908
+ "talker.model.layers.9.input_layernorm.weight": "model.safetensors",
909
+ "talker.model.layers.9.mlp.down_proj.biases": "model.safetensors",
910
+ "talker.model.layers.9.mlp.down_proj.scales": "model.safetensors",
911
+ "talker.model.layers.9.mlp.down_proj.weight": "model.safetensors",
912
+ "talker.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
913
+ "talker.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
914
+ "talker.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
915
+ "talker.model.layers.9.mlp.up_proj.biases": "model.safetensors",
916
+ "talker.model.layers.9.mlp.up_proj.scales": "model.safetensors",
917
+ "talker.model.layers.9.mlp.up_proj.weight": "model.safetensors",
918
+ "talker.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
919
+ "talker.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
920
+ "talker.model.layers.9.self_attn.k_proj.biases": "model.safetensors",
921
+ "talker.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
922
+ "talker.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
923
+ "talker.model.layers.9.self_attn.o_proj.biases": "model.safetensors",
924
+ "talker.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
925
+ "talker.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
926
+ "talker.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
927
+ "talker.model.layers.9.self_attn.q_proj.biases": "model.safetensors",
928
+ "talker.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
929
+ "talker.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
930
+ "talker.model.layers.9.self_attn.v_proj.biases": "model.safetensors",
931
+ "talker.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
932
+ "talker.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
933
+ "talker.model.norm.weight": "model.safetensors",
934
+ "talker.model.text_embedding.biases": "model.safetensors",
935
+ "talker.model.text_embedding.scales": "model.safetensors",
936
+ "talker.model.text_embedding.weight": "model.safetensors",
937
+ "talker.text_projection.linear_fc1.bias": "model.safetensors",
938
+ "talker.text_projection.linear_fc1.biases": "model.safetensors",
939
+ "talker.text_projection.linear_fc1.scales": "model.safetensors",
940
+ "talker.text_projection.linear_fc1.weight": "model.safetensors",
941
+ "talker.text_projection.linear_fc2.bias": "model.safetensors",
942
+ "talker.text_projection.linear_fc2.biases": "model.safetensors",
943
+ "talker.text_projection.linear_fc2.scales": "model.safetensors",
944
+ "talker.text_projection.linear_fc2.weight": "model.safetensors"
945
+ }
946
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "padding_side": "left",
3
+ "padding_value": 0.0,
4
+ "processor_class": "Qwen3TTSProcessor",
5
+ "return_attention_mask": true
6
+ }
speech_tokenizer/config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3TTSTokenizerV2Model"
4
+ ],
5
+ "model_type": "qwen3_tts_tokenizer_12hz",
6
+ "encoder_valid_num_quantizers": 16,
7
+ "input_sample_rate": 24000,
8
+ "output_sample_rate": 24000,
9
+ "decode_upsample_rate": 1920,
10
+ "encode_downsample_rate": 1920,
11
+ "decoder_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "latent_dim": 1024,
15
+ "codebook_dim": 512,
16
+ "codebook_size": 2048,
17
+ "decoder_dim": 1536,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 512,
20
+ "intermediate_size": 1024,
21
+ "layer_scale_initial_scale": 0.01,
22
+ "max_position_embeddings": 8000,
23
+ "head_dim": 64,
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 8,
26
+ "num_key_value_heads": 16,
27
+ "num_quantizers": 16,
28
+ "num_semantic_quantizers": 1,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 10000,
31
+ "semantic_codebook_size": 4096,
32
+ "sliding_window": 72,
33
+ "upsample_rates": [
34
+ 8,
35
+ 5,
36
+ 4,
37
+ 3
38
+ ],
39
+ "upsampling_ratios": [
40
+ 2,
41
+ 2
42
+ ],
43
+ "vector_quantization_hidden_dimension": 512
44
+ },
45
+ "encoder_config": {
46
+ "_frame_rate": 12.5,
47
+ "attention_bias": false,
48
+ "attention_dropout": 0.0,
49
+ "audio_channels": 1,
50
+ "codebook_dim": 256,
51
+ "codebook_size": 2048,
52
+ "compress": 2,
53
+ "dilation_growth_rate": 2,
54
+ "dtype": "float32",
55
+ "head_dim": 64,
56
+ "hidden_act": "gelu",
57
+ "hidden_size": 512,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 2048,
60
+ "kernel_size": 7,
61
+ "last_kernel_size": 3,
62
+ "layer_scale_initial_scale": 0.01,
63
+ "max_position_embeddings": 8000,
64
+ "norm_eps": 1e-05,
65
+ "normalize": false,
66
+ "num_attention_heads": 8,
67
+ "num_filters": 64,
68
+ "num_hidden_layers": 8,
69
+ "num_key_value_heads": 8,
70
+ "num_quantizers": 32,
71
+ "num_residual_layers": 1,
72
+ "num_semantic_quantizers": 1,
73
+ "pad_mode": "constant",
74
+ "residual_kernel_size": 3,
75
+ "rope_theta": 10000.0,
76
+ "sampling_rate": 24000,
77
+ "sliding_window": 250,
78
+ "transformers_version": "4.57.0.dev0",
79
+ "trim_right_ratio": 1.0,
80
+ "upsample_groups": 512,
81
+ "upsampling_ratios": [
82
+ 8,
83
+ 6,
84
+ 5,
85
+ 4
86
+ ],
87
+ "use_cache": false,
88
+ "use_causal_conv": true,
89
+ "use_conv_shortcut": false,
90
+ "use_streaming": false,
91
+ "vector_quantization_hidden_dimension": 256
92
+ },
93
+ "transformers_version": "4.57.3"
94
+ }
speech_tokenizer/configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework": "pytorch", "task": "feature-extraction", "allow_remote": true}
speech_tokenizer/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836b7b357f5ea43e889936a3709af68dfe3751881acefe4ecf0dbd30ba571258
3
+ size 682293092
speech_tokenizer/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 24000
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|audio_pad|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ }
269
+ },
270
+ "additional_special_tokens": [
271
+ "<|im_start|>",
272
+ "<|im_end|>",
273
+ "<|object_ref_start|>",
274
+ "<|object_ref_end|>",
275
+ "<|box_start|>",
276
+ "<|box_end|>",
277
+ "<|quad_start|>",
278
+ "<|quad_end|>",
279
+ "<|vision_start|>",
280
+ "<|vision_end|>",
281
+ "<|vision_pad|>",
282
+ "<|image_pad|>",
283
+ "<|video_pad|>",
284
+ "<|audio_start|>",
285
+ "<|audio_end|>",
286
+ "<tts_pad>",
287
+ "<tts_text_bos>",
288
+ "<tts_text_bos_single>",
289
+ "<|audio_pad|>"
290
+ ],
291
+ "extra_special_tokens": {
292
+ "image_token": "<|image_pad|>",
293
+ "audio_token": "<|audio_pad|>",
294
+ "video_token": "<|video_pad|>",
295
+ "vision_bos_token": "<|vision_start|>",
296
+ "vision_eos_token": "<|vision_end|>",
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>"
299
+ },
300
+ "bos_token": null,
301
+ "clean_up_tokenization_spaces": false,
302
+ "eos_token": "<|im_end|>",
303
+ "errors": "replace",
304
+ "model_max_length": 131072,
305
+ "pad_token": "<|endoftext|>",
306
+ "split_special_tokens": false,
307
+ "tokenizer_class": "Qwen2Tokenizer",
308
+ "unk_token": null,
309
+ "image_token": "<|image_pad|>",
310
+ "audio_token": "<|audio_pad|>",
311
+ "video_token": "<|video_pad|>",
312
+ "vision_bos_token": "<|vision_start|>",
313
+ "vision_eos_token": "<|vision_end|>",
314
+ "audio_bos_token": "<|audio_start|>",
315
+ "audio_eos_token": "<|audio_end|>"
316
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff