Hugging Face's logo

mlx-community
/
Spark-TTS-0.5B-8bit

Text-to-Speech
MLX
Safetensors
English
Chinese
qwen2
8-bit precision
Model card Files
xet
Community
prince-canuma commited on
Commit
0b7dd12
·
verified ·
1 Parent(s): 3270227

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. BiCodec/config.yaml +60 -0
  3. BiCodec/model.safetensors +3 -0
  4. README.md +23 -0
  5. added_tokens.json +0 -0
  6. audio_tokenizer_config.yaml +7 -0
  7. config.json +575 -0
  8. model.safetensors +3 -0
  9. model.safetensors.index.json +635 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +0 -0
  13. vocab.json +0 -0
  14. wav2vec2-large-xlsr-53/config.json +83 -0
  15. wav2vec2-large-xlsr-53/model.safetensors +3 -0
  16. wav2vec2-large-xlsr-53/preprocessor_config.json +9 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
BiCodec/config.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ audio_tokenizer:
2
+ mel_params:
3
+ sample_rate: 16000
4
+ n_fft: 1024
5
+ win_length: 640
6
+ hop_length: 320
7
+ mel_fmin: 10
8
+ mel_fmax: null
9
+ num_mels: 128
10
+
11
+ encoder:
12
+ input_channels: 1024
13
+ vocos_dim: 384
14
+ vocos_intermediate_dim: 2048
15
+ vocos_num_layers: 12
16
+ out_channels: 1024
17
+ sample_ratios: [1,1]
18
+
19
+ decoder:
20
+ input_channel: 1024
21
+ channels: 1536
22
+ rates: [8, 5, 4, 2]
23
+ kernel_sizes: [16,11,8,4]
24
+
25
+ quantizer:
26
+ input_dim: 1024
27
+ codebook_size: 8192
28
+ codebook_dim: 8
29
+ commitment: 0.25
30
+ codebook_loss_weight: 2.0
31
+ use_l2_normlize: True
32
+ threshold_ema_dead_code: 0.2
33
+
34
+ speaker_encoder:
35
+ input_dim: 128
36
+ out_dim: 1024
37
+ latent_dim: 128
38
+ token_num: 32
39
+ fsq_levels: [4, 4, 4, 4, 4, 4]
40
+ fsq_num_quantizers: 1
41
+
42
+ prenet:
43
+ input_channels: 1024
44
+ vocos_dim: 384
45
+ vocos_intermediate_dim: 2048
46
+ vocos_num_layers: 12
47
+ out_channels: 1024
48
+ condition_dim: 1024
49
+ sample_ratios: [1,1]
50
+ use_tanh_at_final: False
51
+
52
+ postnet:
53
+ input_channels: 1024
54
+ vocos_dim: 384
55
+ vocos_intermediate_dim: 2048
56
+ vocos_num_layers: 6
57
+ out_channels: 1024
58
+ use_tanh_at_final: False
59
+
60
+
BiCodec/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9940cd48d4446e4340ced82d234bf5618350dd9f5db900ebe47a4fdb03867ec
3
+ size 625518756
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ language:
4
+ - en
5
+ - zh
6
+ tags:
7
+ - text-to-speech
8
+ - mlx
9
+ library_tag: spark-tts
10
+ ---
11
+
12
+ # mlx-community/Spark-TTS-0.5B-8bit
13
+ This model was converted to MLX format from [`prince-canuma/Spark-TTS-0.5B`](https://huggingface.co/prince-canuma/Spark-TTS-0.5B) using mlx-audio version **0.2.0**.
14
+ Refer to the [original model card](https://huggingface.co/prince-canuma/Spark-TTS-0.5B) for more details on the model.
15
+ ## Use with mlx
16
+
17
+ ```bash
18
+ pip install -U mlx-audio
19
+ ```
20
+
21
+ ```bash
22
+ python -m mlx_audio.tts.generate --model mlx-community/Spark-TTS-0.5B-8bit --text "Describe this image."
23
+ ```
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
audio_tokenizer_config.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ highpass_cutoff_freq: 40
2
+ sample_rate: 16000
3
+ segment_duration: 2.4 # (s)
4
+ max_val_duration: 12 # (s)
5
+ latent_hop_length: 320
6
+ ref_segment_duration: 6
7
+ volume_normalize: true
config.json ADDED
@@ -0,0 +1,575 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bad_words_ids": null,
9
+ "begin_suppress_tokens": null,
10
+ "bos_token_id": 151643,
11
+ "chunk_size_feed_forward": 0,
12
+ "cross_attention_hidden_size": null,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "encoder_no_repeat_ngram_size": 0,
18
+ "eos_token_id": 151645,
19
+ "exponential_decay_length_penalty": null,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 896,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 4864,
31
+ "is_decoder": false,
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "length_penalty": 1.0,
38
+ "max_length": 20,
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 21,
41
+ "min_length": 0,
42
+ "model_type": "qwen2",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_attention_heads": 14,
45
+ "num_beam_groups": 1,
46
+ "num_beams": 1,
47
+ "num_hidden_layers": 24,
48
+ "num_key_value_heads": 2,
49
+ "num_return_sequences": 1,
50
+ "output_attentions": false,
51
+ "output_hidden_states": false,
52
+ "output_scores": false,
53
+ "pad_token_id": null,
54
+ "prefix": null,
55
+ "problem_type": null,
56
+ "pruned_heads": {},
57
+ "quantization": {
58
+ "group_size": 64,
59
+ "bits": 8,
60
+ "model.model.embed_tokens": true,
61
+ "model.model.layers.0.self_attn.q_proj": true,
62
+ "model.model.layers.0.self_attn.k_proj": true,
63
+ "model.model.layers.0.self_attn.v_proj": true,
64
+ "model.model.layers.0.self_attn.o_proj": true,
65
+ "model.model.layers.0.self_attn.rope": false,
66
+ "model.model.layers.0.mlp.gate_proj": true,
67
+ "model.model.layers.0.mlp.down_proj": true,
68
+ "model.model.layers.0.mlp.up_proj": true,
69
+ "model.model.layers.0.input_layernorm": false,
70
+ "model.model.layers.0.post_attention_layernorm": false,
71
+ "model.model.layers.1.self_attn.q_proj": true,
72
+ "model.model.layers.1.self_attn.k_proj": true,
73
+ "model.model.layers.1.self_attn.v_proj": true,
74
+ "model.model.layers.1.self_attn.o_proj": true,
75
+ "model.model.layers.1.self_attn.rope": false,
76
+ "model.model.layers.1.mlp.gate_proj": true,
77
+ "model.model.layers.1.mlp.down_proj": true,
78
+ "model.model.layers.1.mlp.up_proj": true,
79
+ "model.model.layers.1.input_layernorm": false,
80
+ "model.model.layers.1.post_attention_layernorm": false,
81
+ "model.model.layers.2.self_attn.q_proj": true,
82
+ "model.model.layers.2.self_attn.k_proj": true,
83
+ "model.model.layers.2.self_attn.v_proj": true,
84
+ "model.model.layers.2.self_attn.o_proj": true,
85
+ "model.model.layers.2.self_attn.rope": false,
86
+ "model.model.layers.2.mlp.gate_proj": true,
87
+ "model.model.layers.2.mlp.down_proj": true,
88
+ "model.model.layers.2.mlp.up_proj": true,
89
+ "model.model.layers.2.input_layernorm": false,
90
+ "model.model.layers.2.post_attention_layernorm": false,
91
+ "model.model.layers.3.self_attn.q_proj": true,
92
+ "model.model.layers.3.self_attn.k_proj": true,
93
+ "model.model.layers.3.self_attn.v_proj": true,
94
+ "model.model.layers.3.self_attn.o_proj": true,
95
+ "model.model.layers.3.self_attn.rope": false,
96
+ "model.model.layers.3.mlp.gate_proj": true,
97
+ "model.model.layers.3.mlp.down_proj": true,
98
+ "model.model.layers.3.mlp.up_proj": true,
99
+ "model.model.layers.3.input_layernorm": false,
100
+ "model.model.layers.3.post_attention_layernorm": false,
101
+ "model.model.layers.4.self_attn.q_proj": true,
102
+ "model.model.layers.4.self_attn.k_proj": true,
103
+ "model.model.layers.4.self_attn.v_proj": true,
104
+ "model.model.layers.4.self_attn.o_proj": true,
105
+ "model.model.layers.4.self_attn.rope": false,
106
+ "model.model.layers.4.mlp.gate_proj": true,
107
+ "model.model.layers.4.mlp.down_proj": true,
108
+ "model.model.layers.4.mlp.up_proj": true,
109
+ "model.model.layers.4.input_layernorm": false,
110
+ "model.model.layers.4.post_attention_layernorm": false,
111
+ "model.model.layers.5.self_attn.q_proj": true,
112
+ "model.model.layers.5.self_attn.k_proj": true,
113
+ "model.model.layers.5.self_attn.v_proj": true,
114
+ "model.model.layers.5.self_attn.o_proj": true,
115
+ "model.model.layers.5.self_attn.rope": false,
116
+ "model.model.layers.5.mlp.gate_proj": true,
117
+ "model.model.layers.5.mlp.down_proj": true,
118
+ "model.model.layers.5.mlp.up_proj": true,
119
+ "model.model.layers.5.input_layernorm": false,
120
+ "model.model.layers.5.post_attention_layernorm": false,
121
+ "model.model.layers.6.self_attn.q_proj": true,
122
+ "model.model.layers.6.self_attn.k_proj": true,
123
+ "model.model.layers.6.self_attn.v_proj": true,
124
+ "model.model.layers.6.self_attn.o_proj": true,
125
+ "model.model.layers.6.self_attn.rope": false,
126
+ "model.model.layers.6.mlp.gate_proj": true,
127
+ "model.model.layers.6.mlp.down_proj": true,
128
+ "model.model.layers.6.mlp.up_proj": true,
129
+ "model.model.layers.6.input_layernorm": false,
130
+ "model.model.layers.6.post_attention_layernorm": false,
131
+ "model.model.layers.7.self_attn.q_proj": true,
132
+ "model.model.layers.7.self_attn.k_proj": true,
133
+ "model.model.layers.7.self_attn.v_proj": true,
134
+ "model.model.layers.7.self_attn.o_proj": true,
135
+ "model.model.layers.7.self_attn.rope": false,
136
+ "model.model.layers.7.mlp.gate_proj": true,
137
+ "model.model.layers.7.mlp.down_proj": true,
138
+ "model.model.layers.7.mlp.up_proj": true,
139
+ "model.model.layers.7.input_layernorm": false,
140
+ "model.model.layers.7.post_attention_layernorm": false,
141
+ "model.model.layers.8.self_attn.q_proj": true,
142
+ "model.model.layers.8.self_attn.k_proj": true,
143
+ "model.model.layers.8.self_attn.v_proj": true,
144
+ "model.model.layers.8.self_attn.o_proj": true,
145
+ "model.model.layers.8.self_attn.rope": false,
146
+ "model.model.layers.8.mlp.gate_proj": true,
147
+ "model.model.layers.8.mlp.down_proj": true,
148
+ "model.model.layers.8.mlp.up_proj": true,
149
+ "model.model.layers.8.input_layernorm": false,
150
+ "model.model.layers.8.post_attention_layernorm": false,
151
+ "model.model.layers.9.self_attn.q_proj": true,
152
+ "model.model.layers.9.self_attn.k_proj": true,
153
+ "model.model.layers.9.self_attn.v_proj": true,
154
+ "model.model.layers.9.self_attn.o_proj": true,
155
+ "model.model.layers.9.self_attn.rope": false,
156
+ "model.model.layers.9.mlp.gate_proj": true,
157
+ "model.model.layers.9.mlp.down_proj": true,
158
+ "model.model.layers.9.mlp.up_proj": true,
159
+ "model.model.layers.9.input_layernorm": false,
160
+ "model.model.layers.9.post_attention_layernorm": false,
161
+ "model.model.layers.10.self_attn.q_proj": true,
162
+ "model.model.layers.10.self_attn.k_proj": true,
163
+ "model.model.layers.10.self_attn.v_proj": true,
164
+ "model.model.layers.10.self_attn.o_proj": true,
165
+ "model.model.layers.10.self_attn.rope": false,
166
+ "model.model.layers.10.mlp.gate_proj": true,
167
+ "model.model.layers.10.mlp.down_proj": true,
168
+ "model.model.layers.10.mlp.up_proj": true,
169
+ "model.model.layers.10.input_layernorm": false,
170
+ "model.model.layers.10.post_attention_layernorm": false,
171
+ "model.model.layers.11.self_attn.q_proj": true,
172
+ "model.model.layers.11.self_attn.k_proj": true,
173
+ "model.model.layers.11.self_attn.v_proj": true,
174
+ "model.model.layers.11.self_attn.o_proj": true,
175
+ "model.model.layers.11.self_attn.rope": false,
176
+ "model.model.layers.11.mlp.gate_proj": true,
177
+ "model.model.layers.11.mlp.down_proj": true,
178
+ "model.model.layers.11.mlp.up_proj": true,
179
+ "model.model.layers.11.input_layernorm": false,
180
+ "model.model.layers.11.post_attention_layernorm": false,
181
+ "model.model.layers.12.self_attn.q_proj": true,
182
+ "model.model.layers.12.self_attn.k_proj": true,
183
+ "model.model.layers.12.self_attn.v_proj": true,
184
+ "model.model.layers.12.self_attn.o_proj": true,
185
+ "model.model.layers.12.self_attn.rope": false,
186
+ "model.model.layers.12.mlp.gate_proj": true,
187
+ "model.model.layers.12.mlp.down_proj": true,
188
+ "model.model.layers.12.mlp.up_proj": true,
189
+ "model.model.layers.12.input_layernorm": false,
190
+ "model.model.layers.12.post_attention_layernorm": false,
191
+ "model.model.layers.13.self_attn.q_proj": true,
192
+ "model.model.layers.13.self_attn.k_proj": true,
193
+ "model.model.layers.13.self_attn.v_proj": true,
194
+ "model.model.layers.13.self_attn.o_proj": true,
195
+ "model.model.layers.13.self_attn.rope": false,
196
+ "model.model.layers.13.mlp.gate_proj": true,
197
+ "model.model.layers.13.mlp.down_proj": true,
198
+ "model.model.layers.13.mlp.up_proj": true,
199
+ "model.model.layers.13.input_layernorm": false,
200
+ "model.model.layers.13.post_attention_layernorm": false,
201
+ "model.model.layers.14.self_attn.q_proj": true,
202
+ "model.model.layers.14.self_attn.k_proj": true,
203
+ "model.model.layers.14.self_attn.v_proj": true,
204
+ "model.model.layers.14.self_attn.o_proj": true,
205
+ "model.model.layers.14.self_attn.rope": false,
206
+ "model.model.layers.14.mlp.gate_proj": true,
207
+ "model.model.layers.14.mlp.down_proj": true,
208
+ "model.model.layers.14.mlp.up_proj": true,
209
+ "model.model.layers.14.input_layernorm": false,
210
+ "model.model.layers.14.post_attention_layernorm": false,
211
+ "model.model.layers.15.self_attn.q_proj": true,
212
+ "model.model.layers.15.self_attn.k_proj": true,
213
+ "model.model.layers.15.self_attn.v_proj": true,
214
+ "model.model.layers.15.self_attn.o_proj": true,
215
+ "model.model.layers.15.self_attn.rope": false,
216
+ "model.model.layers.15.mlp.gate_proj": true,
217
+ "model.model.layers.15.mlp.down_proj": true,
218
+ "model.model.layers.15.mlp.up_proj": true,
219
+ "model.model.layers.15.input_layernorm": false,
220
+ "model.model.layers.15.post_attention_layernorm": false,
221
+ "model.model.layers.16.self_attn.q_proj": true,
222
+ "model.model.layers.16.self_attn.k_proj": true,
223
+ "model.model.layers.16.self_attn.v_proj": true,
224
+ "model.model.layers.16.self_attn.o_proj": true,
225
+ "model.model.layers.16.self_attn.rope": false,
226
+ "model.model.layers.16.mlp.gate_proj": true,
227
+ "model.model.layers.16.mlp.down_proj": true,
228
+ "model.model.layers.16.mlp.up_proj": true,
229
+ "model.model.layers.16.input_layernorm": false,
230
+ "model.model.layers.16.post_attention_layernorm": false,
231
+ "model.model.layers.17.self_attn.q_proj": true,
232
+ "model.model.layers.17.self_attn.k_proj": true,
233
+ "model.model.layers.17.self_attn.v_proj": true,
234
+ "model.model.layers.17.self_attn.o_proj": true,
235
+ "model.model.layers.17.self_attn.rope": false,
236
+ "model.model.layers.17.mlp.gate_proj": true,
237
+ "model.model.layers.17.mlp.down_proj": true,
238
+ "model.model.layers.17.mlp.up_proj": true,
239
+ "model.model.layers.17.input_layernorm": false,
240
+ "model.model.layers.17.post_attention_layernorm": false,
241
+ "model.model.layers.18.self_attn.q_proj": true,
242
+ "model.model.layers.18.self_attn.k_proj": true,
243
+ "model.model.layers.18.self_attn.v_proj": true,
244
+ "model.model.layers.18.self_attn.o_proj": true,
245
+ "model.model.layers.18.self_attn.rope": false,
246
+ "model.model.layers.18.mlp.gate_proj": true,
247
+ "model.model.layers.18.mlp.down_proj": true,
248
+ "model.model.layers.18.mlp.up_proj": true,
249
+ "model.model.layers.18.input_layernorm": false,
250
+ "model.model.layers.18.post_attention_layernorm": false,
251
+ "model.model.layers.19.self_attn.q_proj": true,
252
+ "model.model.layers.19.self_attn.k_proj": true,
253
+ "model.model.layers.19.self_attn.v_proj": true,
254
+ "model.model.layers.19.self_attn.o_proj": true,
255
+ "model.model.layers.19.self_attn.rope": false,
256
+ "model.model.layers.19.mlp.gate_proj": true,
257
+ "model.model.layers.19.mlp.down_proj": true,
258
+ "model.model.layers.19.mlp.up_proj": true,
259
+ "model.model.layers.19.input_layernorm": false,
260
+ "model.model.layers.19.post_attention_layernorm": false,
261
+ "model.model.layers.20.self_attn.q_proj": true,
262
+ "model.model.layers.20.self_attn.k_proj": true,
263
+ "model.model.layers.20.self_attn.v_proj": true,
264
+ "model.model.layers.20.self_attn.o_proj": true,
265
+ "model.model.layers.20.self_attn.rope": false,
266
+ "model.model.layers.20.mlp.gate_proj": true,
267
+ "model.model.layers.20.mlp.down_proj": true,
268
+ "model.model.layers.20.mlp.up_proj": true,
269
+ "model.model.layers.20.input_layernorm": false,
270
+ "model.model.layers.20.post_attention_layernorm": false,
271
+ "model.model.layers.21.self_attn.q_proj": true,
272
+ "model.model.layers.21.self_attn.k_proj": true,
273
+ "model.model.layers.21.self_attn.v_proj": true,
274
+ "model.model.layers.21.self_attn.o_proj": true,
275
+ "model.model.layers.21.self_attn.rope": false,
276
+ "model.model.layers.21.mlp.gate_proj": true,
277
+ "model.model.layers.21.mlp.down_proj": true,
278
+ "model.model.layers.21.mlp.up_proj": true,
279
+ "model.model.layers.21.input_layernorm": false,
280
+ "model.model.layers.21.post_attention_layernorm": false,
281
+ "model.model.layers.22.self_attn.q_proj": true,
282
+ "model.model.layers.22.self_attn.k_proj": true,
283
+ "model.model.layers.22.self_attn.v_proj": true,
284
+ "model.model.layers.22.self_attn.o_proj": true,
285
+ "model.model.layers.22.self_attn.rope": false,
286
+ "model.model.layers.22.mlp.gate_proj": true,
287
+ "model.model.layers.22.mlp.down_proj": true,
288
+ "model.model.layers.22.mlp.up_proj": true,
289
+ "model.model.layers.22.input_layernorm": false,
290
+ "model.model.layers.22.post_attention_layernorm": false,
291
+ "model.model.layers.23.self_attn.q_proj": true,
292
+ "model.model.layers.23.self_attn.k_proj": true,
293
+ "model.model.layers.23.self_attn.v_proj": true,
294
+ "model.model.layers.23.self_attn.o_proj": true,
295
+ "model.model.layers.23.self_attn.rope": false,
296
+ "model.model.layers.23.mlp.gate_proj": true,
297
+ "model.model.layers.23.mlp.down_proj": true,
298
+ "model.model.layers.23.mlp.up_proj": true,
299
+ "model.model.layers.23.input_layernorm": false,
300
+ "model.model.layers.23.post_attention_layernorm": false,
301
+ "model.model.norm": false
302
+ },
303
+ "quantization_config": {
304
+ "group_size": 64,
305
+ "bits": 8,
306
+ "model.model.embed_tokens": true,
307
+ "model.model.layers.0.self_attn.q_proj": true,
308
+ "model.model.layers.0.self_attn.k_proj": true,
309
+ "model.model.layers.0.self_attn.v_proj": true,
310
+ "model.model.layers.0.self_attn.o_proj": true,
311
+ "model.model.layers.0.self_attn.rope": false,
312
+ "model.model.layers.0.mlp.gate_proj": true,
313
+ "model.model.layers.0.mlp.down_proj": true,
314
+ "model.model.layers.0.mlp.up_proj": true,
315
+ "model.model.layers.0.input_layernorm": false,
316
+ "model.model.layers.0.post_attention_layernorm": false,
317
+ "model.model.layers.1.self_attn.q_proj": true,
318
+ "model.model.layers.1.self_attn.k_proj": true,
319
+ "model.model.layers.1.self_attn.v_proj": true,
320
+ "model.model.layers.1.self_attn.o_proj": true,
321
+ "model.model.layers.1.self_attn.rope": false,
322
+ "model.model.layers.1.mlp.gate_proj": true,
323
+ "model.model.layers.1.mlp.down_proj": true,
324
+ "model.model.layers.1.mlp.up_proj": true,
325
+ "model.model.layers.1.input_layernorm": false,
326
+ "model.model.layers.1.post_attention_layernorm": false,
327
+ "model.model.layers.2.self_attn.q_proj": true,
328
+ "model.model.layers.2.self_attn.k_proj": true,
329
+ "model.model.layers.2.self_attn.v_proj": true,
330
+ "model.model.layers.2.self_attn.o_proj": true,
331
+ "model.model.layers.2.self_attn.rope": false,
332
+ "model.model.layers.2.mlp.gate_proj": true,
333
+ "model.model.layers.2.mlp.down_proj": true,
334
+ "model.model.layers.2.mlp.up_proj": true,
335
+ "model.model.layers.2.input_layernorm": false,
336
+ "model.model.layers.2.post_attention_layernorm": false,
337
+ "model.model.layers.3.self_attn.q_proj": true,
338
+ "model.model.layers.3.self_attn.k_proj": true,
339
+ "model.model.layers.3.self_attn.v_proj": true,
340
+ "model.model.layers.3.self_attn.o_proj": true,
341
+ "model.model.layers.3.self_attn.rope": false,
342
+ "model.model.layers.3.mlp.gate_proj": true,
343
+ "model.model.layers.3.mlp.down_proj": true,
344
+ "model.model.layers.3.mlp.up_proj": true,
345
+ "model.model.layers.3.input_layernorm": false,
346
+ "model.model.layers.3.post_attention_layernorm": false,
347
+ "model.model.layers.4.self_attn.q_proj": true,
348
+ "model.model.layers.4.self_attn.k_proj": true,
349
+ "model.model.layers.4.self_attn.v_proj": true,
350
+ "model.model.layers.4.self_attn.o_proj": true,
351
+ "model.model.layers.4.self_attn.rope": false,
352
+ "model.model.layers.4.mlp.gate_proj": true,
353
+ "model.model.layers.4.mlp.down_proj": true,
354
+ "model.model.layers.4.mlp.up_proj": true,
355
+ "model.model.layers.4.input_layernorm": false,
356
+ "model.model.layers.4.post_attention_layernorm": false,
357
+ "model.model.layers.5.self_attn.q_proj": true,
358
+ "model.model.layers.5.self_attn.k_proj": true,
359
+ "model.model.layers.5.self_attn.v_proj": true,
360
+ "model.model.layers.5.self_attn.o_proj": true,
361
+ "model.model.layers.5.self_attn.rope": false,
362
+ "model.model.layers.5.mlp.gate_proj": true,
363
+ "model.model.layers.5.mlp.down_proj": true,
364
+ "model.model.layers.5.mlp.up_proj": true,
365
+ "model.model.layers.5.input_layernorm": false,
366
+ "model.model.layers.5.post_attention_layernorm": false,
367
+ "model.model.layers.6.self_attn.q_proj": true,
368
+ "model.model.layers.6.self_attn.k_proj": true,
369
+ "model.model.layers.6.self_attn.v_proj": true,
370
+ "model.model.layers.6.self_attn.o_proj": true,
371
+ "model.model.layers.6.self_attn.rope": false,
372
+ "model.model.layers.6.mlp.gate_proj": true,
373
+ "model.model.layers.6.mlp.down_proj": true,
374
+ "model.model.layers.6.mlp.up_proj": true,
375
+ "model.model.layers.6.input_layernorm": false,
376
+ "model.model.layers.6.post_attention_layernorm": false,
377
+ "model.model.layers.7.self_attn.q_proj": true,
378
+ "model.model.layers.7.self_attn.k_proj": true,
379
+ "model.model.layers.7.self_attn.v_proj": true,
380
+ "model.model.layers.7.self_attn.o_proj": true,
381
+ "model.model.layers.7.self_attn.rope": false,
382
+ "model.model.layers.7.mlp.gate_proj": true,
383
+ "model.model.layers.7.mlp.down_proj": true,
384
+ "model.model.layers.7.mlp.up_proj": true,
385
+ "model.model.layers.7.input_layernorm": false,
386
+ "model.model.layers.7.post_attention_layernorm": false,
387
+ "model.model.layers.8.self_attn.q_proj": true,
388
+ "model.model.layers.8.self_attn.k_proj": true,
389
+ "model.model.layers.8.self_attn.v_proj": true,
390
+ "model.model.layers.8.self_attn.o_proj": true,
391
+ "model.model.layers.8.self_attn.rope": false,
392
+ "model.model.layers.8.mlp.gate_proj": true,
393
+ "model.model.layers.8.mlp.down_proj": true,
394
+ "model.model.layers.8.mlp.up_proj": true,
395
+ "model.model.layers.8.input_layernorm": false,
396
+ "model.model.layers.8.post_attention_layernorm": false,
397
+ "model.model.layers.9.self_attn.q_proj": true,
398
+ "model.model.layers.9.self_attn.k_proj": true,
399
+ "model.model.layers.9.self_attn.v_proj": true,
400
+ "model.model.layers.9.self_attn.o_proj": true,
401
+ "model.model.layers.9.self_attn.rope": false,
402
+ "model.model.layers.9.mlp.gate_proj": true,
403
+ "model.model.layers.9.mlp.down_proj": true,
404
+ "model.model.layers.9.mlp.up_proj": true,
405
+ "model.model.layers.9.input_layernorm": false,
406
+ "model.model.layers.9.post_attention_layernorm": false,
407
+ "model.model.layers.10.self_attn.q_proj": true,
408
+ "model.model.layers.10.self_attn.k_proj": true,
409
+ "model.model.layers.10.self_attn.v_proj": true,
410
+ "model.model.layers.10.self_attn.o_proj": true,
411
+ "model.model.layers.10.self_attn.rope": false,
412
+ "model.model.layers.10.mlp.gate_proj": true,
413
+ "model.model.layers.10.mlp.down_proj": true,
414
+ "model.model.layers.10.mlp.up_proj": true,
415
+ "model.model.layers.10.input_layernorm": false,
416
+ "model.model.layers.10.post_attention_layernorm": false,
417
+ "model.model.layers.11.self_attn.q_proj": true,
418
+ "model.model.layers.11.self_attn.k_proj": true,
419
+ "model.model.layers.11.self_attn.v_proj": true,
420
+ "model.model.layers.11.self_attn.o_proj": true,
421
+ "model.model.layers.11.self_attn.rope": false,
422
+ "model.model.layers.11.mlp.gate_proj": true,
423
+ "model.model.layers.11.mlp.down_proj": true,
424
+ "model.model.layers.11.mlp.up_proj": true,
425
+ "model.model.layers.11.input_layernorm": false,
426
+ "model.model.layers.11.post_attention_layernorm": false,
427
+ "model.model.layers.12.self_attn.q_proj": true,
428
+ "model.model.layers.12.self_attn.k_proj": true,
429
+ "model.model.layers.12.self_attn.v_proj": true,
430
+ "model.model.layers.12.self_attn.o_proj": true,
431
+ "model.model.layers.12.self_attn.rope": false,
432
+ "model.model.layers.12.mlp.gate_proj": true,
433
+ "model.model.layers.12.mlp.down_proj": true,
434
+ "model.model.layers.12.mlp.up_proj": true,
435
+ "model.model.layers.12.input_layernorm": false,
436
+ "model.model.layers.12.post_attention_layernorm": false,
437
+ "model.model.layers.13.self_attn.q_proj": true,
438
+ "model.model.layers.13.self_attn.k_proj": true,
439
+ "model.model.layers.13.self_attn.v_proj": true,
440
+ "model.model.layers.13.self_attn.o_proj": true,
441
+ "model.model.layers.13.self_attn.rope": false,
442
+ "model.model.layers.13.mlp.gate_proj": true,
443
+ "model.model.layers.13.mlp.down_proj": true,
444
+ "model.model.layers.13.mlp.up_proj": true,
445
+ "model.model.layers.13.input_layernorm": false,
446
+ "model.model.layers.13.post_attention_layernorm": false,
447
+ "model.model.layers.14.self_attn.q_proj": true,
448
+ "model.model.layers.14.self_attn.k_proj": true,
449
+ "model.model.layers.14.self_attn.v_proj": true,
450
+ "model.model.layers.14.self_attn.o_proj": true,
451
+ "model.model.layers.14.self_attn.rope": false,
452
+ "model.model.layers.14.mlp.gate_proj": true,
453
+ "model.model.layers.14.mlp.down_proj": true,
454
+ "model.model.layers.14.mlp.up_proj": true,
455
+ "model.model.layers.14.input_layernorm": false,
456
+ "model.model.layers.14.post_attention_layernorm": false,
457
+ "model.model.layers.15.self_attn.q_proj": true,
458
+ "model.model.layers.15.self_attn.k_proj": true,
459
+ "model.model.layers.15.self_attn.v_proj": true,
460
+ "model.model.layers.15.self_attn.o_proj": true,
461
+ "model.model.layers.15.self_attn.rope": false,
462
+ "model.model.layers.15.mlp.gate_proj": true,
463
+ "model.model.layers.15.mlp.down_proj": true,
464
+ "model.model.layers.15.mlp.up_proj": true,
465
+ "model.model.layers.15.input_layernorm": false,
466
+ "model.model.layers.15.post_attention_layernorm": false,
467
+ "model.model.layers.16.self_attn.q_proj": true,
468
+ "model.model.layers.16.self_attn.k_proj": true,
469
+ "model.model.layers.16.self_attn.v_proj": true,
470
+ "model.model.layers.16.self_attn.o_proj": true,
471
+ "model.model.layers.16.self_attn.rope": false,
472
+ "model.model.layers.16.mlp.gate_proj": true,
473
+ "model.model.layers.16.mlp.down_proj": true,
474
+ "model.model.layers.16.mlp.up_proj": true,
475
+ "model.model.layers.16.input_layernorm": false,
476
+ "model.model.layers.16.post_attention_layernorm": false,
477
+ "model.model.layers.17.self_attn.q_proj": true,
478
+ "model.model.layers.17.self_attn.k_proj": true,
479
+ "model.model.layers.17.self_attn.v_proj": true,
480
+ "model.model.layers.17.self_attn.o_proj": true,
481
+ "model.model.layers.17.self_attn.rope": false,
482
+ "model.model.layers.17.mlp.gate_proj": true,
483
+ "model.model.layers.17.mlp.down_proj": true,
484
+ "model.model.layers.17.mlp.up_proj": true,
485
+ "model.model.layers.17.input_layernorm": false,
486
+ "model.model.layers.17.post_attention_layernorm": false,
487
+ "model.model.layers.18.self_attn.q_proj": true,
488
+ "model.model.layers.18.self_attn.k_proj": true,
489
+ "model.model.layers.18.self_attn.v_proj": true,
490
+ "model.model.layers.18.self_attn.o_proj": true,
491
+ "model.model.layers.18.self_attn.rope": false,
492
+ "model.model.layers.18.mlp.gate_proj": true,
493
+ "model.model.layers.18.mlp.down_proj": true,
494
+ "model.model.layers.18.mlp.up_proj": true,
495
+ "model.model.layers.18.input_layernorm": false,
496
+ "model.model.layers.18.post_attention_layernorm": false,
497
+ "model.model.layers.19.self_attn.q_proj": true,
498
+ "model.model.layers.19.self_attn.k_proj": true,
499
+ "model.model.layers.19.self_attn.v_proj": true,
500
+ "model.model.layers.19.self_attn.o_proj": true,
501
+ "model.model.layers.19.self_attn.rope": false,
502
+ "model.model.layers.19.mlp.gate_proj": true,
503
+ "model.model.layers.19.mlp.down_proj": true,
504
+ "model.model.layers.19.mlp.up_proj": true,
505
+ "model.model.layers.19.input_layernorm": false,
506
+ "model.model.layers.19.post_attention_layernorm": false,
507
+ "model.model.layers.20.self_attn.q_proj": true,
508
+ "model.model.layers.20.self_attn.k_proj": true,
509
+ "model.model.layers.20.self_attn.v_proj": true,
510
+ "model.model.layers.20.self_attn.o_proj": true,
511
+ "model.model.layers.20.self_attn.rope": false,
512
+ "model.model.layers.20.mlp.gate_proj": true,
513
+ "model.model.layers.20.mlp.down_proj": true,
514
+ "model.model.layers.20.mlp.up_proj": true,
515
+ "model.model.layers.20.input_layernorm": false,
516
+ "model.model.layers.20.post_attention_layernorm": false,
517
+ "model.model.layers.21.self_attn.q_proj": true,
518
+ "model.model.layers.21.self_attn.k_proj": true,
519
+ "model.model.layers.21.self_attn.v_proj": true,
520
+ "model.model.layers.21.self_attn.o_proj": true,
521
+ "model.model.layers.21.self_attn.rope": false,
522
+ "model.model.layers.21.mlp.gate_proj": true,
523
+ "model.model.layers.21.mlp.down_proj": true,
524
+ "model.model.layers.21.mlp.up_proj": true,
525
+ "model.model.layers.21.input_layernorm": false,
526
+ "model.model.layers.21.post_attention_layernorm": false,
527
+ "model.model.layers.22.self_attn.q_proj": true,
528
+ "model.model.layers.22.self_attn.k_proj": true,
529
+ "model.model.layers.22.self_attn.v_proj": true,
530
+ "model.model.layers.22.self_attn.o_proj": true,
531
+ "model.model.layers.22.self_attn.rope": false,
532
+ "model.model.layers.22.mlp.gate_proj": true,
533
+ "model.model.layers.22.mlp.down_proj": true,
534
+ "model.model.layers.22.mlp.up_proj": true,
535
+ "model.model.layers.22.input_layernorm": false,
536
+ "model.model.layers.22.post_attention_layernorm": false,
537
+ "model.model.layers.23.self_attn.q_proj": true,
538
+ "model.model.layers.23.self_attn.k_proj": true,
539
+ "model.model.layers.23.self_attn.v_proj": true,
540
+ "model.model.layers.23.self_attn.o_proj": true,
541
+ "model.model.layers.23.self_attn.rope": false,
542
+ "model.model.layers.23.mlp.gate_proj": true,
543
+ "model.model.layers.23.mlp.down_proj": true,
544
+ "model.model.layers.23.mlp.up_proj": true,
545
+ "model.model.layers.23.input_layernorm": false,
546
+ "model.model.layers.23.post_attention_layernorm": false,
547
+ "model.model.norm": false
548
+ },
549
+ "remove_invalid_values": false,
550
+ "repetition_penalty": 1.0,
551
+ "return_dict": true,
552
+ "return_dict_in_generate": false,
553
+ "rms_norm_eps": 1e-06,
554
+ "rope_scaling": null,
555
+ "rope_theta": 1000000.0,
556
+ "sep_token_id": null,
557
+ "sliding_window": 32768,
558
+ "suppress_tokens": null,
559
+ "task_specific_params": null,
560
+ "temperature": 1.0,
561
+ "tf_legacy_loss": false,
562
+ "tie_encoder_decoder": false,
563
+ "tie_word_embeddings": true,
564
+ "tokenizer_class": null,
565
+ "top_k": 50,
566
+ "top_p": 1.0,
567
+ "torch_dtype": "bfloat16",
568
+ "torchscript": false,
569
+ "transformers_version": "4.51.3",
570
+ "typical_p": 1.0,
571
+ "use_bfloat16": false,
572
+ "use_cache": true,
573
+ "use_sliding_window": false,
574
+ "vocab_size": 166000
575
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02a2f85a3f9b8dbd758d887640d622d946a4247339138eb7eccde5e7cb9a25c
3
+ size 538435169
model.safetensors.index.json ADDED
@@ -0,0 +1,635 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 538365824
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.biases": "model.safetensors",
7
+ "model.embed_tokens.scales": "model.safetensors",
8
+ "model.embed_tokens.weight": "model.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
10
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
11
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
12
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
13
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
14
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
15
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
16
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
17
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
18
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
19
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
20
+ "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
21
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
22
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
23
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
24
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
25
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
26
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
27
+ "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
28
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
29
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
30
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
31
+ "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
32
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
33
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
34
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
35
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
36
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
37
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
38
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
39
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
40
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
41
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
42
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
43
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
44
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
45
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
46
+ "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
47
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
48
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
49
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
50
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
51
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
52
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
53
+ "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
54
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
55
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
56
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
57
+ "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
58
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
59
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
60
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
61
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
62
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
63
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
64
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
65
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
66
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
67
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
68
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
69
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
70
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
71
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
72
+ "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
73
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
74
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
75
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
76
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
77
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
78
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
79
+ "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
80
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
81
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
82
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
83
+ "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
84
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
85
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
86
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
87
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
88
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
89
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
90
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
91
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
92
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
93
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
94
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
95
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
96
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
97
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
98
+ "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
99
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
100
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
101
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
102
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
103
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
104
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
105
+ "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
106
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
107
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
108
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
109
+ "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
110
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
111
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
112
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
113
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
114
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
115
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
116
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
117
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
118
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
119
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
120
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
121
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
122
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
123
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
124
+ "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
125
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
126
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
127
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
128
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
129
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
130
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
131
+ "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
132
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
133
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
134
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
135
+ "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
136
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
137
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
138
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
139
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
140
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
141
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
142
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
143
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
144
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
145
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
146
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
147
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
148
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
149
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
150
+ "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
151
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
152
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
153
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
154
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
155
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
156
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
157
+ "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
158
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
159
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
160
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
161
+ "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
162
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
163
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
164
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
165
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
166
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
167
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
168
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
169
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
170
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
171
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
172
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
173
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
174
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
175
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
176
+ "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
177
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
178
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
179
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
180
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
181
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
182
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
183
+ "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
184
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
185
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
186
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
187
+ "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
188
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
189
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
190
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
191
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
192
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
193
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
194
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
195
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
196
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
197
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
198
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
199
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
200
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
201
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
202
+ "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
203
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
204
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
205
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
206
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
207
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
208
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
209
+ "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
210
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
211
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
212
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
213
+ "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
214
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
215
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
216
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
217
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
218
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
219
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
220
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
221
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
222
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
223
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
224
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
225
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
226
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
227
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
228
+ "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
229
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
230
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
231
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
232
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
233
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
234
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
235
+ "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
236
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
237
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
238
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
239
+ "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
240
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
241
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
242
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
243
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
244
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
245
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
246
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
247
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
248
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
249
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
250
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
251
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
252
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
253
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
254
+ "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
255
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
256
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
257
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
258
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
259
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
260
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
261
+ "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
262
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
263
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
264
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
265
+ "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
266
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
267
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
268
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
269
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
270
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
271
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
272
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
273
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
274
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
275
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
276
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
277
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
278
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
279
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
280
+ "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
281
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
282
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
283
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
284
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
285
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
286
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
287
+ "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
288
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
289
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
290
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
291
+ "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
292
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
293
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
294
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
295
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
296
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
297
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
298
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
299
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
300
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
301
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
302
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
303
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
304
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
305
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
306
+ "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
307
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
308
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
309
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
310
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
311
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
312
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
313
+ "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
314
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
315
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
316
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
317
+ "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
318
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
319
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
320
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
321
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
322
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
323
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
324
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
325
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
326
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
327
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
328
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
329
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
330
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
331
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
332
+ "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
333
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
334
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
335
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
336
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
337
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
338
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
339
+ "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
340
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
341
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
342
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
343
+ "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
344
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
345
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
346
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
347
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
348
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
349
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
350
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
351
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
352
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
353
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
354
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
355
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
356
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
357
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
358
+ "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
359
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
360
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
361
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
362
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
363
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
364
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
365
+ "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
366
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
367
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
368
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
369
+ "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
370
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
371
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
372
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
373
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
374
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
375
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
376
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
377
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
378
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
379
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
380
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
381
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
382
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
383
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
384
+ "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
385
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
386
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
387
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
388
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
389
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
390
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
391
+ "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
392
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
393
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
394
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
395
+ "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
396
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
397
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
398
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
399
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
400
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
401
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
402
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
403
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
404
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
405
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
406
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
407
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
408
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
409
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
410
+ "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
411
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
412
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
413
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
414
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
415
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
416
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
417
+ "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
418
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
419
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
420
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
421
+ "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
422
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
423
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
424
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
425
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
426
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
427
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
428
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
429
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
430
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
431
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
432
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
433
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
434
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
435
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
436
+ "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
437
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
438
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
439
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
440
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
441
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
442
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
443
+ "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
444
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
445
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
446
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
447
+ "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
448
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
449
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
450
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
451
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
452
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
453
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
454
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
455
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
456
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
457
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
458
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
459
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
460
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
461
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
462
+ "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
463
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
464
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
465
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
466
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
467
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
468
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
469
+ "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
470
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
471
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
472
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
473
+ "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
474
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
475
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
476
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
477
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
478
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
479
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
480
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
481
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
482
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
483
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
484
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
485
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
486
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
487
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
488
+ "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
489
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
490
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
491
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
492
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
493
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
494
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
495
+ "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
496
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
497
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
498
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
499
+ "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
500
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
501
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
502
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
503
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
504
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
505
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
506
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
507
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
508
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
509
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
510
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
511
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
512
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
513
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
514
+ "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
515
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
516
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
517
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
518
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
519
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
520
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
521
+ "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
522
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
523
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
524
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
525
+ "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
526
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
527
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
528
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
529
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
530
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
531
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
532
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
533
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
534
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
535
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
536
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
537
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
538
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
539
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
540
+ "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
541
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
542
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
543
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
544
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
545
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
546
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
547
+ "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
548
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
549
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
550
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
551
+ "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
552
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
553
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
554
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
555
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
556
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
557
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
558
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
559
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
560
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
561
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
562
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
563
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
564
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
565
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
566
+ "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
567
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
568
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
569
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
570
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
571
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
572
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
573
+ "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
574
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
575
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
576
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
577
+ "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
578
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
579
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
580
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
581
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
582
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
583
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
584
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
585
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
586
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
587
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
588
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
589
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
590
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
591
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
592
+ "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
593
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
594
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
595
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
596
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
597
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
598
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
599
+ "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
600
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
601
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
602
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
603
+ "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
604
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
605
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
606
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
607
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
608
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
609
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
610
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
611
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
612
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
613
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
614
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
615
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
616
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
617
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
618
+ "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
619
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
620
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
621
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
622
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
623
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
624
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
625
+ "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
626
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
627
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
628
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
629
+ "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
630
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
631
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
632
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
633
+ "model.norm.weight": "model.safetensors"
634
+ }
635
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8b057d6ca205a429cc3428b9fc815f0d6ee1d53106dd5e5b129ef9db2ff057
3
+ size 14129172
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
wav2vec2-large-xlsr-53/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForPreTraining"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "codevector_dim": 768,
10
+ "contrastive_logits_temperature": 0.1,
11
+ "conv_bias": true,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "diversity_loss_weight": 0.1,
42
+ "do_stable_layer_norm": true,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.0,
46
+ "feat_extract_norm": "layer",
47
+ "feat_proj_dropout": 0.1,
48
+ "feat_quantizer_dropout": 0.0,
49
+ "final_dropout": 0.0,
50
+ "gradient_checkpointing": false,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_size": 1024,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 4096,
56
+ "layer_norm_eps": 1e-05,
57
+ "layerdrop": 0.1,
58
+ "mask_channel_length": 10,
59
+ "mask_channel_min_space": 1,
60
+ "mask_channel_other": 0.0,
61
+ "mask_channel_prob": 0.0,
62
+ "mask_channel_selection": "static",
63
+ "mask_feature_length": 10,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_space": 1,
67
+ "mask_time_other": 0.0,
68
+ "mask_time_prob": 0.075,
69
+ "mask_time_selection": "static",
70
+ "model_type": "wav2vec2",
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "pad_token_id": 0,
80
+ "proj_codevector_dim": 768,
81
+ "transformers_version": "4.7.0.dev0",
82
+ "vocab_size": 32
83
+ }
wav2vec2-large-xlsr-53/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8b60ccc08ffcd555abc1df8e113228b9956e855034f4287d8c4ab7ae8b53ba
3
+ size 1261803488
wav2vec2-large-xlsr-53/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }