Muhammadreza commited on
Commit
8c3b7b9
0 Parent(s):

Initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +35 -0
  2. README.md +62 -0
  3. config.json +296 -0
  4. generation_config.json +10 -0
  5. onnx/build_delay_pattern_mask.onnx +3 -0
  6. onnx/build_delay_pattern_mask_bnb4.onnx +3 -0
  7. onnx/build_delay_pattern_mask_fp16.onnx +3 -0
  8. onnx/build_delay_pattern_mask_int8.onnx +3 -0
  9. onnx/build_delay_pattern_mask_q4.onnx +3 -0
  10. onnx/build_delay_pattern_mask_quantized.onnx +3 -0
  11. onnx/build_delay_pattern_mask_uint8.onnx +3 -0
  12. onnx/decoder_model.onnx +3 -0
  13. onnx/decoder_model_bnb4.onnx +3 -0
  14. onnx/decoder_model_fp16.onnx +3 -0
  15. onnx/decoder_model_int8.onnx +3 -0
  16. onnx/decoder_model_merged.onnx +3 -0
  17. onnx/decoder_model_merged_bnb4.onnx +3 -0
  18. onnx/decoder_model_merged_fp16.onnx +3 -0
  19. onnx/decoder_model_merged_int8.onnx +3 -0
  20. onnx/decoder_model_merged_q4.onnx +3 -0
  21. onnx/decoder_model_merged_quantized.onnx +3 -0
  22. onnx/decoder_model_merged_uint8.onnx +3 -0
  23. onnx/decoder_model_q4.onnx +3 -0
  24. onnx/decoder_model_quantized.onnx +3 -0
  25. onnx/decoder_model_uint8.onnx +3 -0
  26. onnx/decoder_with_past_model.onnx +3 -0
  27. onnx/decoder_with_past_model_bnb4.onnx +3 -0
  28. onnx/decoder_with_past_model_fp16.onnx +3 -0
  29. onnx/decoder_with_past_model_int8.onnx +3 -0
  30. onnx/decoder_with_past_model_q4.onnx +3 -0
  31. onnx/decoder_with_past_model_quantized.onnx +3 -0
  32. onnx/decoder_with_past_model_uint8.onnx +3 -0
  33. onnx/encodec_decode.onnx +3 -0
  34. onnx/encodec_decode_bnb4.onnx +3 -0
  35. onnx/encodec_decode_fp16.onnx +3 -0
  36. onnx/encodec_decode_int8.onnx +3 -0
  37. onnx/encodec_decode_q4.onnx +3 -0
  38. onnx/encodec_decode_quantized.onnx +3 -0
  39. onnx/encodec_decode_uint8.onnx +3 -0
  40. onnx/text_encoder.onnx +3 -0
  41. onnx/text_encoder_bnb4.onnx +3 -0
  42. onnx/text_encoder_fp16.onnx +3 -0
  43. onnx/text_encoder_int8.onnx +3 -0
  44. onnx/text_encoder_q4.onnx +3 -0
  45. onnx/text_encoder_quantized.onnx +3 -0
  46. onnx/text_encoder_uint8.onnx +3 -0
  47. preprocessor_config.json +11 -0
  48. quantize_config.json +558 -0
  49. special_tokens_map.json +125 -0
  50. spiece.model +3 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers.js
3
+ license: cc-by-nc-4.0
4
+ ---
5
+
6
+ https://huggingface.co/facebook/musicgen-small with ONNX weights to be compatible with Transformers.js.
7
+
8
+ ## Usage (Transformers.js)
9
+
10
+ > [!IMPORTANT]
11
+ > NOTE: MusicGen support is experimental and requires you to install Transformers.js [v3](https://github.com/xenova/transformers.js/tree/v3) from source.
12
+
13
+ If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [GitHub](https://github.com/xenova/transformers.js/tree/v3) using:
14
+ ```bash
15
+ npm install xenova/transformers.js#v3
16
+ ```
17
+
18
+ **Example:** Generate music with `Xenova/musicgen-small`.
19
+ ```js
20
+ import { AutoTokenizer, MusicgenForConditionalGeneration } from '@xenova/transformers';
21
+
22
+ // Load tokenizer and model
23
+ const tokenizer = await AutoTokenizer.from_pretrained('Xenova/musicgen-small');
24
+ const model = await MusicgenForConditionalGeneration.from_pretrained('Xenova/musicgen-small', {
25
+ dtype: {
26
+ text_encoder: 'q8',
27
+ decoder_model_merged: 'q8',
28
+ encodec_decode: 'fp32',
29
+ },
30
+ });
31
+
32
+ // Prepare text input
33
+ const prompt = 'a light and cheerly EDM track, with syncopated drums, aery pads, and strong emotions bpm: 130';
34
+ const inputs = tokenizer(prompt);
35
+
36
+ // Generate audio
37
+ const audio_values = await model.generate({
38
+ ...inputs,
39
+ max_new_tokens: 500,
40
+ do_sample: true,
41
+ guidance_scale: 3,
42
+ });
43
+
44
+ // (Optional) Write the output to a WAV file
45
+ import wavefile from 'wavefile';
46
+ import fs from 'fs';
47
+
48
+ const wav = new wavefile.WaveFile();
49
+ wav.fromScratch(1, model.config.audio_encoder.sampling_rate, '32f', audio_values.data);
50
+ fs.writeFileSync('musicgen.wav', wav.toBuffer());
51
+ ```
52
+
53
+ <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/61b253b7ac5ecaae3d1efe0c/cJ9HFIDstOqJN0eGyJwlS.wav"></audio>
54
+
55
+ We also released an online demo, which you can try yourself: https://huggingface.co/spaces/Xenova/musicgen-web
56
+
57
+
58
+ <video controls src="https://cdn-uploads.huggingface.co/production/uploads/61b253b7ac5ecaae3d1efe0c/zc43B_VuUVJm4kOJPOHNh.mp4"></video>
59
+
60
+ ---
61
+
62
+ Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
config.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/musicgen-small",
3
+ "architectures": [
4
+ "MusicgenForConditionalGeneration"
5
+ ],
6
+ "audio_encoder": {
7
+ "_name_or_path": "facebook/encodec_32khz",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "EncodecModel"
11
+ ],
12
+ "audio_channels": 1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_length_s": null,
17
+ "chunk_size_feed_forward": 0,
18
+ "codebook_dim": 128,
19
+ "codebook_size": 2048,
20
+ "compress": 2,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "dilation_growth_rate": 2,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": null,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_size": 128,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "kernel_size": 7,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "last_kernel_size": 7,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "min_length": 0,
49
+ "model_type": "encodec",
50
+ "no_repeat_ngram_size": 0,
51
+ "norm_type": "weight_norm",
52
+ "normalize": false,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_filters": 64,
56
+ "num_lstm_layers": 2,
57
+ "num_residual_layers": 1,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "overlap": null,
63
+ "pad_mode": "reflect",
64
+ "pad_token_id": null,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "residual_kernel_size": 3,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sampling_rate": 32000,
74
+ "sep_token_id": null,
75
+ "suppress_tokens": null,
76
+ "target_bandwidths": [
77
+ 2.2
78
+ ],
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": "float32",
88
+ "torchscript": false,
89
+ "trim_right_ratio": 1.0,
90
+ "typical_p": 1.0,
91
+ "upsampling_ratios": [
92
+ 8,
93
+ 5,
94
+ 4,
95
+ 4
96
+ ],
97
+ "use_bfloat16": false,
98
+ "use_causal_conv": false,
99
+ "use_conv_shortcut": false
100
+ },
101
+ "decoder": {
102
+ "_name_or_path": "",
103
+ "activation_dropout": 0.0,
104
+ "activation_function": "gelu",
105
+ "add_cross_attention": false,
106
+ "architectures": null,
107
+ "attention_dropout": 0.0,
108
+ "audio_channels": 1,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 2048,
112
+ "chunk_size_feed_forward": 0,
113
+ "classifier_dropout": 0.0,
114
+ "cross_attention_hidden_size": null,
115
+ "decoder_start_token_id": null,
116
+ "diversity_penalty": 0.0,
117
+ "do_sample": false,
118
+ "dropout": 0.1,
119
+ "early_stopping": false,
120
+ "encoder_no_repeat_ngram_size": 0,
121
+ "eos_token_id": null,
122
+ "exponential_decay_length_penalty": null,
123
+ "ffn_dim": 4096,
124
+ "finetuning_task": null,
125
+ "forced_bos_token_id": null,
126
+ "forced_eos_token_id": null,
127
+ "hidden_size": 1024,
128
+ "id2label": {
129
+ "0": "LABEL_0",
130
+ "1": "LABEL_1"
131
+ },
132
+ "initializer_factor": 0.02,
133
+ "is_decoder": false,
134
+ "is_encoder_decoder": false,
135
+ "label2id": {
136
+ "LABEL_0": 0,
137
+ "LABEL_1": 1
138
+ },
139
+ "layerdrop": 0.0,
140
+ "length_penalty": 1.0,
141
+ "max_length": 20,
142
+ "max_position_embeddings": 2048,
143
+ "min_length": 0,
144
+ "model_type": "musicgen_decoder",
145
+ "no_repeat_ngram_size": 0,
146
+ "num_attention_heads": 16,
147
+ "num_beam_groups": 1,
148
+ "num_beams": 1,
149
+ "num_codebooks": 4,
150
+ "num_hidden_layers": 24,
151
+ "num_return_sequences": 1,
152
+ "output_attentions": false,
153
+ "output_hidden_states": false,
154
+ "output_scores": false,
155
+ "pad_token_id": 2048,
156
+ "prefix": null,
157
+ "problem_type": null,
158
+ "pruned_heads": {},
159
+ "remove_invalid_values": false,
160
+ "repetition_penalty": 1.0,
161
+ "return_dict": true,
162
+ "return_dict_in_generate": false,
163
+ "scale_embedding": false,
164
+ "sep_token_id": null,
165
+ "suppress_tokens": null,
166
+ "task_specific_params": null,
167
+ "temperature": 1.0,
168
+ "tf_legacy_loss": false,
169
+ "tie_encoder_decoder": false,
170
+ "tie_word_embeddings": false,
171
+ "tokenizer_class": null,
172
+ "top_k": 50,
173
+ "top_p": 1.0,
174
+ "torch_dtype": null,
175
+ "torchscript": false,
176
+ "typical_p": 1.0,
177
+ "use_bfloat16": false,
178
+ "use_cache": true,
179
+ "vocab_size": 2048
180
+ },
181
+ "is_encoder_decoder": true,
182
+ "model_type": "musicgen",
183
+ "text_encoder": {
184
+ "_name_or_path": "t5-base",
185
+ "add_cross_attention": false,
186
+ "architectures": [
187
+ "T5ForConditionalGeneration"
188
+ ],
189
+ "bad_words_ids": null,
190
+ "begin_suppress_tokens": null,
191
+ "bos_token_id": null,
192
+ "chunk_size_feed_forward": 0,
193
+ "classifier_dropout": 0.0,
194
+ "cross_attention_hidden_size": null,
195
+ "d_ff": 3072,
196
+ "d_kv": 64,
197
+ "d_model": 768,
198
+ "decoder_start_token_id": 0,
199
+ "dense_act_fn": "relu",
200
+ "diversity_penalty": 0.0,
201
+ "do_sample": false,
202
+ "dropout_rate": 0.1,
203
+ "early_stopping": false,
204
+ "encoder_no_repeat_ngram_size": 0,
205
+ "eos_token_id": 1,
206
+ "exponential_decay_length_penalty": null,
207
+ "feed_forward_proj": "relu",
208
+ "finetuning_task": null,
209
+ "forced_bos_token_id": null,
210
+ "forced_eos_token_id": null,
211
+ "id2label": {
212
+ "0": "LABEL_0",
213
+ "1": "LABEL_1"
214
+ },
215
+ "initializer_factor": 1.0,
216
+ "is_decoder": false,
217
+ "is_encoder_decoder": true,
218
+ "is_gated_act": false,
219
+ "label2id": {
220
+ "LABEL_0": 0,
221
+ "LABEL_1": 1
222
+ },
223
+ "layer_norm_epsilon": 1e-06,
224
+ "length_penalty": 1.0,
225
+ "max_length": 20,
226
+ "min_length": 0,
227
+ "model_type": "t5",
228
+ "n_positions": 512,
229
+ "no_repeat_ngram_size": 0,
230
+ "num_beam_groups": 1,
231
+ "num_beams": 1,
232
+ "num_decoder_layers": 12,
233
+ "num_heads": 12,
234
+ "num_layers": 12,
235
+ "num_return_sequences": 1,
236
+ "output_attentions": false,
237
+ "output_hidden_states": false,
238
+ "output_past": true,
239
+ "output_scores": false,
240
+ "pad_token_id": 0,
241
+ "prefix": null,
242
+ "problem_type": null,
243
+ "pruned_heads": {},
244
+ "relative_attention_max_distance": 128,
245
+ "relative_attention_num_buckets": 32,
246
+ "remove_invalid_values": false,
247
+ "repetition_penalty": 1.0,
248
+ "return_dict": true,
249
+ "return_dict_in_generate": false,
250
+ "sep_token_id": null,
251
+ "suppress_tokens": null,
252
+ "task_specific_params": {
253
+ "summarization": {
254
+ "early_stopping": true,
255
+ "length_penalty": 2.0,
256
+ "max_length": 200,
257
+ "min_length": 30,
258
+ "no_repeat_ngram_size": 3,
259
+ "num_beams": 4,
260
+ "prefix": "summarize: "
261
+ },
262
+ "translation_en_to_de": {
263
+ "early_stopping": true,
264
+ "max_length": 300,
265
+ "num_beams": 4,
266
+ "prefix": "translate English to German: "
267
+ },
268
+ "translation_en_to_fr": {
269
+ "early_stopping": true,
270
+ "max_length": 300,
271
+ "num_beams": 4,
272
+ "prefix": "translate English to French: "
273
+ },
274
+ "translation_en_to_ro": {
275
+ "early_stopping": true,
276
+ "max_length": 300,
277
+ "num_beams": 4,
278
+ "prefix": "translate English to Romanian: "
279
+ }
280
+ },
281
+ "temperature": 1.0,
282
+ "tf_legacy_loss": false,
283
+ "tie_encoder_decoder": false,
284
+ "tie_word_embeddings": true,
285
+ "tokenizer_class": null,
286
+ "top_k": 50,
287
+ "top_p": 1.0,
288
+ "torch_dtype": null,
289
+ "torchscript": false,
290
+ "typical_p": 1.0,
291
+ "use_bfloat16": false,
292
+ "use_cache": true,
293
+ "vocab_size": 32128
294
+ },
295
+ "transformers_version": "4.40.0.dev0"
296
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2048,
4
+ "decoder_start_token_id": 2048,
5
+ "do_sample": true,
6
+ "guidance_scale": 3.0,
7
+ "max_length": 1500,
8
+ "pad_token_id": 2048,
9
+ "transformers_version": "4.40.0.dev0"
10
+ }
onnx/build_delay_pattern_mask.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84edae5bef3bfba3aad4f1e3e786dc120857cb8db136e3b9f68e4eb1a4cfeac7
3
+ size 35360
onnx/build_delay_pattern_mask_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c988ded727c85d0c396b97cc7e79ffe5bb1a294f9c7f6e19df75d83d576d0b
3
+ size 35379
onnx/build_delay_pattern_mask_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4acc38a235d6c9499915095905bfd4b02bb4c62039f487c44084c63846d2059c
3
+ size 52053
onnx/build_delay_pattern_mask_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4997af816452ed9c9e1c9a7f8c02cd613e235e02a179a2a0f6f3a8b0fb628e0e
3
+ size 52092
onnx/build_delay_pattern_mask_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c988ded727c85d0c396b97cc7e79ffe5bb1a294f9c7f6e19df75d83d576d0b
3
+ size 35379
onnx/build_delay_pattern_mask_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4997af816452ed9c9e1c9a7f8c02cd613e235e02a179a2a0f6f3a8b0fb628e0e
3
+ size 52092
onnx/build_delay_pattern_mask_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4997af816452ed9c9e1c9a7f8c02cd613e235e02a179a2a0f6f3a8b0fb628e0e
3
+ size 52092
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8497084fd0d4f7733ae1fa481c6d39f5130e32eff27da717fa07c6e7deb1af71
3
+ size 1691136293
onnx/decoder_model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f907283b2cc5dd902d8321f6f89013055efd471eb2d9dd145c6097f55e3390d6
3
+ size 275515156
onnx/decoder_model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50aebf05bf038e95a2ea6948f5bacf7865e36fca7e179fa5cd586f3d0ba48bae
3
+ size 846702678
onnx/decoder_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52ff6681bc2b74ef3326584cd9e74ff6949742ca61efaf5b41ada412e1b8919
3
+ size 424993274
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2cf8b839b2e48b480e264972931e9f6b7f7d6d1483fb00a03ad6c4bda64121
3
+ size 1692230645
onnx/decoder_model_merged_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b258352f011dbd2717a6cb838ceccf488daca5e818e19230c2d9443d0362a1c
3
+ size 276638222
onnx/decoder_model_merged_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9098bd6b5195626455db10198681b84b1f002033d53294d5f4df5b6faf1da365
3
+ size 848232814
onnx/decoder_model_merged_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0784dfa87ac4cba563c01a081f22841e782bdbe91ce751b5cc955f6c499c4c6
3
+ size 426777507
onnx/decoder_model_merged_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78915f801eb40fb323fa2362ffc97bdf05099eaf21b14f5441e13813ef5eef38
3
+ size 302373739
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dade5431ef5f3690cde7449d8e881b2d596d1ee5c6472752787d7d470d67091
3
+ size 428422300
onnx/decoder_model_merged_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7ce852f6a9b5b4af113c6f3da41361dbdde62b5986b8da5f7f939646b498d9
3
+ size 426777627
onnx/decoder_model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b11f3bd74a4a5ef3315468d5af225c9b51d3fe2b9417d1e43682260713e3e4
3
+ size 301252437
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3fff451a7f89ae5a7e547ffa3b7933e5116f56ee928b75277d2d451418e9b09
3
+ size 426638067
onnx/decoder_model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5315e5d595e184d470e36467df93dd86bcdf1bbe5b5f5c3530fa818bdd1a691c
3
+ size 424993394
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05501e600138f1d09220f994f924280f5b403aab503e6989acbf8ec3456e2637
3
+ size 1486479458
onnx/decoder_with_past_model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7723ccfdb919a9c5a78a6f0db57d2769abf32d2c233ea6994c00ab1b52da5355
3
+ size 246569076
onnx/decoder_with_past_model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c32661a2843568bc569f8fc66d05e5b6c5fcf4bd2ec88db898277c38e5ab30f
3
+ size 744224406
onnx/decoder_with_past_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f079fa848c6a21ba458fee27968c7a165e0d56d4f1e81658d7b370f466e8449
3
+ size 373572413
onnx/decoder_with_past_model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dade76da136404a69a134af3f0ec0da3a3d875ad18e81ce7861cade5f808bc1
3
+ size 269111869
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f013ec948fa4f8731c13af8fdcd24a83a5fa8e4891d5a651cfb3c11cba08c6
3
+ size 374966081
onnx/decoder_with_past_model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34151320cd6e680c391b16ffb6a22932675ac534bbffd1484769cb89d89519fb
3
+ size 373572507
onnx/encodec_decode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847918300a85c9a8f93333f482c5740e07c4e2599faed839bbec73fd0d588073
3
+ size 118056304
onnx/encodec_decode_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12cad95eb6dfd867cb75e2735a497beb38361a9a2e4dae385a4a51b9396ac235
3
+ size 118056323
onnx/encodec_decode_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a10aa50de680d50e13e3cb85e358bad31427c98ce9ee9cd2596af6576620a7b9
3
+ size 59125087
onnx/encodec_decode_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bc9dd34b782aa667bbf2d83f25b31ec19db39aadc55a61e4161736c98c99bf
3
+ size 59796619
onnx/encodec_decode_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12cad95eb6dfd867cb75e2735a497beb38361a9a2e4dae385a4a51b9396ac235
3
+ size 118056323
onnx/encodec_decode_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2a729fd329ad5390f209234c697f56c8d8f03ee6c273959b7adbccd2d4ac66
3
+ size 59878565
onnx/encodec_decode_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5d97ab43fba9152418343efd9e61fe1eb3d00175cf8e97b124f661ac77d54b
3
+ size 59796623
onnx/text_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7962c2408b03ebb37252e6d1a3179517e8c6127b9fda4e0beab84dfa09aab80
3
+ size 438689759
onnx/text_encoder_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef68265cc3aa0cd351f33de7a57785dfc8c85d1396d567ffb2426c937383ca0
3
+ size 146738081
onnx/text_encoder_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0fdd8b8b3edc877e1ecefcabe1cad24d8d299a92ea208b1d9c732f9b63753ed
3
+ size 219508053
onnx/text_encoder_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77494d927d25ea09e6abc8d566281b5b9cd58f39c5f89a7da60e157b0a711607
3
+ size 110027935
onnx/text_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac0a3b4e96068e2563fb15e1dd8b882934b208329eacefd8be7eb755595733f4
3
+ size 152045969
onnx/text_encoder_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336afda84d24205409f20e71da691e5c21585e32aa86e3e38d73543ac6d481fc
3
+ size 110443015
onnx/text_encoder_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4473292627f012bce6714118bcf22095eb4dcbf85ba140b5cb10b51de0d04c5e
3
+ size 110027971
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "left",
7
+ "padding_value": 0.0,
8
+ "processor_class": "MusicgenProcessor",
9
+ "return_attention_mask": true,
10
+ "sampling_rate": 32000
11
+ }
quantize_config.json ADDED
@@ -0,0 +1,558 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "Add",
8
+ "Cast",
9
+ "Concat",
10
+ "Constant",
11
+ "ConstantOfShape",
12
+ "Div",
13
+ "Equal",
14
+ "Erf",
15
+ "Expand",
16
+ "Gather",
17
+ "If",
18
+ "Less",
19
+ "MatMul",
20
+ "Mul",
21
+ "Pow",
22
+ "Range",
23
+ "ReduceMean",
24
+ "Reshape",
25
+ "Shape",
26
+ "Slice",
27
+ "Softmax",
28
+ "Sqrt",
29
+ "Squeeze",
30
+ "Sub",
31
+ "Transpose",
32
+ "Unsqueeze",
33
+ "Where"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model": {
38
+ "op_types": [
39
+ "Add",
40
+ "Cast",
41
+ "Concat",
42
+ "Constant",
43
+ "ConstantOfShape",
44
+ "Div",
45
+ "Equal",
46
+ "Erf",
47
+ "Expand",
48
+ "Gather",
49
+ "Less",
50
+ "MatMul",
51
+ "Mul",
52
+ "Pow",
53
+ "Range",
54
+ "ReduceMean",
55
+ "Reshape",
56
+ "Shape",
57
+ "Slice",
58
+ "Softmax",
59
+ "Sqrt",
60
+ "Squeeze",
61
+ "Sub",
62
+ "Transpose",
63
+ "Unsqueeze",
64
+ "Where"
65
+ ],
66
+ "weight_type": "QInt8"
67
+ },
68
+ "text_encoder": {
69
+ "op_types": [
70
+ "Abs",
71
+ "Add",
72
+ "Cast",
73
+ "Concat",
74
+ "Constant",
75
+ "ConstantOfShape",
76
+ "Div",
77
+ "Gather",
78
+ "Greater",
79
+ "Less",
80
+ "Log",
81
+ "MatMul",
82
+ "Min",
83
+ "Mul",
84
+ "Pow",
85
+ "Range",
86
+ "ReduceMean",
87
+ "Relu",
88
+ "Reshape",
89
+ "Shape",
90
+ "Softmax",
91
+ "Sqrt",
92
+ "Sub",
93
+ "Transpose",
94
+ "Unsqueeze",
95
+ "Where"
96
+ ],
97
+ "weight_type": "QInt8"
98
+ },
99
+ "decoder_with_past_model": {
100
+ "op_types": [
101
+ "Add",
102
+ "Cast",
103
+ "Concat",
104
+ "Constant",
105
+ "ConstantOfShape",
106
+ "Div",
107
+ "Equal",
108
+ "Erf",
109
+ "Expand",
110
+ "Gather",
111
+ "MatMul",
112
+ "Mul",
113
+ "Pow",
114
+ "Range",
115
+ "ReduceMean",
116
+ "Reshape",
117
+ "Shape",
118
+ "Softmax",
119
+ "Sqrt",
120
+ "Sub",
121
+ "Transpose",
122
+ "Unsqueeze",
123
+ "Where"
124
+ ],
125
+ "weight_type": "QInt8"
126
+ },
127
+ "encodec_decode": {
128
+ "op_types": [
129
+ "Add",
130
+ "Cast",
131
+ "Ceil",
132
+ "Concat",
133
+ "Constant",
134
+ "ConstantOfShape",
135
+ "Conv",
136
+ "ConvTranspose",
137
+ "Div",
138
+ "Elu",
139
+ "Gather",
140
+ "LSTM",
141
+ "Pad",
142
+ "Reshape",
143
+ "Shape",
144
+ "Slice",
145
+ "Split",
146
+ "Squeeze",
147
+ "Sub",
148
+ "Transpose",
149
+ "Unsqueeze"
150
+ ],
151
+ "weight_type": "QUInt8"
152
+ },
153
+ "build_delay_pattern_mask": {
154
+ "op_types": [
155
+ "Add",
156
+ "Cast",
157
+ "Concat",
158
+ "Constant",
159
+ "ConstantOfShape",
160
+ "Equal",
161
+ "Expand",
162
+ "Gather",
163
+ "GreaterOrEqual",
164
+ "Mul",
165
+ "NonZero",
166
+ "Not",
167
+ "Range",
168
+ "ReduceMin",
169
+ "Reshape",
170
+ "ScatterND",
171
+ "Shape",
172
+ "Slice",
173
+ "Sub",
174
+ "Transpose",
175
+ "Trilu",
176
+ "Unsqueeze",
177
+ "Where"
178
+ ],
179
+ "weight_type": "QInt8"
180
+ }
181
+ },
182
+ "per_channel": true,
183
+ "reduce_range": true
184
+ },
185
+ "int8": {
186
+ "per_model_config": {
187
+ "decoder_model_merged": {
188
+ "op_types": [
189
+ "Add",
190
+ "Cast",
191
+ "Concat",
192
+ "Constant",
193
+ "ConstantOfShape",
194
+ "Div",
195
+ "Equal",
196
+ "Erf",
197
+ "Expand",
198
+ "Gather",
199
+ "If",
200
+ "Less",
201
+ "MatMul",
202
+ "Mul",
203
+ "Pow",
204
+ "Range",
205
+ "ReduceMean",
206
+ "Reshape",
207
+ "Shape",
208
+ "Slice",
209
+ "Softmax",
210
+ "Sqrt",
211
+ "Squeeze",
212
+ "Sub",
213
+ "Transpose",
214
+ "Unsqueeze",
215
+ "Where"
216
+ ],
217
+ "weight_type": "QInt8"
218
+ },
219
+ "decoder_model": {
220
+ "op_types": [
221
+ "Add",
222
+ "Cast",
223
+ "Concat",
224
+ "Constant",
225
+ "ConstantOfShape",
226
+ "Div",
227
+ "Equal",
228
+ "Erf",
229
+ "Expand",
230
+ "Gather",
231
+ "Less",
232
+ "MatMul",
233
+ "Mul",
234
+ "Pow",
235
+ "Range",
236
+ "ReduceMean",
237
+ "Reshape",
238
+ "Shape",
239
+ "Slice",
240
+ "Softmax",
241
+ "Sqrt",
242
+ "Squeeze",
243
+ "Sub",
244
+ "Transpose",
245
+ "Unsqueeze",
246
+ "Where"
247
+ ],
248
+ "weight_type": "QInt8"
249
+ },
250
+ "text_encoder": {
251
+ "op_types": [
252
+ "Abs",
253
+ "Add",
254
+ "Cast",
255
+ "Concat",
256
+ "Constant",
257
+ "ConstantOfShape",
258
+ "Div",
259
+ "Gather",
260
+ "Greater",
261
+ "Less",
262
+ "Log",
263
+ "MatMul",
264
+ "Min",
265
+ "Mul",
266
+ "Pow",
267
+ "Range",
268
+ "ReduceMean",
269
+ "Relu",
270
+ "Reshape",
271
+ "Shape",
272
+ "Softmax",
273
+ "Sqrt",
274
+ "Sub",
275
+ "Transpose",
276
+ "Unsqueeze",
277
+ "Where"
278
+ ],
279
+ "weight_type": "QInt8"
280
+ },
281
+ "decoder_with_past_model": {
282
+ "op_types": [
283
+ "Add",
284
+ "Cast",
285
+ "Concat",
286
+ "Constant",
287
+ "ConstantOfShape",
288
+ "Div",
289
+ "Equal",
290
+ "Erf",
291
+ "Expand",
292
+ "Gather",
293
+ "MatMul",
294
+ "Mul",
295
+ "Pow",
296
+ "Range",
297
+ "ReduceMean",
298
+ "Reshape",
299
+ "Shape",
300
+ "Softmax",
301
+ "Sqrt",
302
+ "Sub",
303
+ "Transpose",
304
+ "Unsqueeze",
305
+ "Where"
306
+ ],
307
+ "weight_type": "QInt8"
308
+ },
309
+ "encodec_decode": {
310
+ "op_types": [
311
+ "Add",
312
+ "Cast",
313
+ "Ceil",
314
+ "Concat",
315
+ "Constant",
316
+ "ConstantOfShape",
317
+ "Conv",
318
+ "ConvTranspose",
319
+ "Div",
320
+ "Elu",
321
+ "Gather",
322
+ "LSTM",
323
+ "Pad",
324
+ "Reshape",
325
+ "Shape",
326
+ "Slice",
327
+ "Split",
328
+ "Squeeze",
329
+ "Sub",
330
+ "Transpose",
331
+ "Unsqueeze"
332
+ ],
333
+ "weight_type": "QInt8"
334
+ },
335
+ "build_delay_pattern_mask": {
336
+ "op_types": [
337
+ "Add",
338
+ "Cast",
339
+ "Concat",
340
+ "Constant",
341
+ "ConstantOfShape",
342
+ "Equal",
343
+ "Expand",
344
+ "Gather",
345
+ "GreaterOrEqual",
346
+ "Mul",
347
+ "NonZero",
348
+ "Not",
349
+ "Range",
350
+ "ReduceMin",
351
+ "Reshape",
352
+ "ScatterND",
353
+ "Shape",
354
+ "Slice",
355
+ "Sub",
356
+ "Transpose",
357
+ "Trilu",
358
+ "Unsqueeze",
359
+ "Where"
360
+ ],
361
+ "weight_type": "QInt8"
362
+ }
363
+ },
364
+ "per_channel": false,
365
+ "reduce_range": false
366
+ },
367
+ "uint8": {
368
+ "per_model_config": {
369
+ "decoder_model_merged": {
370
+ "op_types": [
371
+ "Add",
372
+ "Cast",
373
+ "Concat",
374
+ "Constant",
375
+ "ConstantOfShape",
376
+ "Div",
377
+ "Equal",
378
+ "Erf",
379
+ "Expand",
380
+ "Gather",
381
+ "If",
382
+ "Less",
383
+ "MatMul",
384
+ "Mul",
385
+ "Pow",
386
+ "Range",
387
+ "ReduceMean",
388
+ "Reshape",
389
+ "Shape",
390
+ "Slice",
391
+ "Softmax",
392
+ "Sqrt",
393
+ "Squeeze",
394
+ "Sub",
395
+ "Transpose",
396
+ "Unsqueeze",
397
+ "Where"
398
+ ],
399
+ "weight_type": "QUInt8"
400
+ },
401
+ "decoder_model": {
402
+ "op_types": [
403
+ "Add",
404
+ "Cast",
405
+ "Concat",
406
+ "Constant",
407
+ "ConstantOfShape",
408
+ "Div",
409
+ "Equal",
410
+ "Erf",
411
+ "Expand",
412
+ "Gather",
413
+ "Less",
414
+ "MatMul",
415
+ "Mul",
416
+ "Pow",
417
+ "Range",
418
+ "ReduceMean",
419
+ "Reshape",
420
+ "Shape",
421
+ "Slice",
422
+ "Softmax",
423
+ "Sqrt",
424
+ "Squeeze",
425
+ "Sub",
426
+ "Transpose",
427
+ "Unsqueeze",
428
+ "Where"
429
+ ],
430
+ "weight_type": "QUInt8"
431
+ },
432
+ "text_encoder": {
433
+ "op_types": [
434
+ "Abs",
435
+ "Add",
436
+ "Cast",
437
+ "Concat",
438
+ "Constant",
439
+ "ConstantOfShape",
440
+ "Div",
441
+ "Gather",
442
+ "Greater",
443
+ "Less",
444
+ "Log",
445
+ "MatMul",
446
+ "Min",
447
+ "Mul",
448
+ "Pow",
449
+ "Range",
450
+ "ReduceMean",
451
+ "Relu",
452
+ "Reshape",
453
+ "Shape",
454
+ "Softmax",
455
+ "Sqrt",
456
+ "Sub",
457
+ "Transpose",
458
+ "Unsqueeze",
459
+ "Where"
460
+ ],
461
+ "weight_type": "QUInt8"
462
+ },
463
+ "decoder_with_past_model": {
464
+ "op_types": [
465
+ "Add",
466
+ "Cast",
467
+ "Concat",
468
+ "Constant",
469
+ "ConstantOfShape",
470
+ "Div",
471
+ "Equal",
472
+ "Erf",
473
+ "Expand",
474
+ "Gather",
475
+ "MatMul",
476
+ "Mul",
477
+ "Pow",
478
+ "Range",
479
+ "ReduceMean",
480
+ "Reshape",
481
+ "Shape",
482
+ "Softmax",
483
+ "Sqrt",
484
+ "Sub",
485
+ "Transpose",
486
+ "Unsqueeze",
487
+ "Where"
488
+ ],
489
+ "weight_type": "QUInt8"
490
+ },
491
+ "encodec_decode": {
492
+ "op_types": [
493
+ "Add",
494
+ "Cast",
495
+ "Ceil",
496
+ "Concat",
497
+ "Constant",
498
+ "ConstantOfShape",
499
+ "Conv",
500
+ "ConvTranspose",
501
+ "Div",
502
+ "Elu",
503
+ "Gather",
504
+ "LSTM",
505
+ "Pad",
506
+ "Reshape",
507
+ "Shape",
508
+ "Slice",
509
+ "Split",
510
+ "Squeeze",
511
+ "Sub",
512
+ "Transpose",
513
+ "Unsqueeze"
514
+ ],
515
+ "weight_type": "QUInt8"
516
+ },
517
+ "build_delay_pattern_mask": {
518
+ "op_types": [
519
+ "Add",
520
+ "Cast",
521
+ "Concat",
522
+ "Constant",
523
+ "ConstantOfShape",
524
+ "Equal",
525
+ "Expand",
526
+ "Gather",
527
+ "GreaterOrEqual",
528
+ "Mul",
529
+ "NonZero",
530
+ "Not",
531
+ "Range",
532
+ "ReduceMin",
533
+ "Reshape",
534
+ "ScatterND",
535
+ "Shape",
536
+ "Slice",
537
+ "Sub",
538
+ "Transpose",
539
+ "Trilu",
540
+ "Unsqueeze",
541
+ "Where"
542
+ ],
543
+ "weight_type": "QUInt8"
544
+ }
545
+ },
546
+ "per_channel": false,
547
+ "reduce_range": false
548
+ },
549
+ "bnb4": {
550
+ "block_size": 64,
551
+ "quant_type": 1
552
+ },
553
+ "q4": {
554
+ "block_size": 32,
555
+ "is_symmetric": true,
556
+ "accuracy_level": null
557
+ }
558
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656