Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers.js
+license: cc-by-nc-4.0
+---
+
+https://huggingface.co/facebook/musicgen-small with ONNX weights to be compatible with Transformers.js.
+
+## Usage (Transformers.js)
+
+> [!IMPORTANT]
+> NOTE: MusicGen support is experimental and requires you to install Transformers.js [v3](https://github.com/xenova/transformers.js/tree/v3) from source.
+
+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:
+```bash
+npm install xenova/transformers.js#v3
+```
+
+**Example:** Generate music with `Xenova/musicgen-small`.
+```js
+import { AutoTokenizer, MusicgenForConditionalGeneration } from '@xenova/transformers';
+
+// Load tokenizer and model
+const tokenizer = await AutoTokenizer.from_pretrained('Xenova/musicgen-small');
+const model = await MusicgenForConditionalGeneration.from_pretrained('Xenova/musicgen-small', {
+  dtype: {
+    text_encoder: 'q8',
+    decoder_model_merged: 'q8',
+    encodec_decode: 'fp32',
+  },
+});
+
+// Prepare text input
+const prompt = 'a light and cheerly EDM track, with syncopated drums, aery pads, and strong emotions bpm: 130';
+const inputs = tokenizer(prompt);
+
+// Generate audio
+const audio_values = await model.generate({
+  ...inputs,
+  max_new_tokens: 500,
+  do_sample: true,
+  guidance_scale: 3,
+});
+
+// (Optional) Write the output to a WAV file
+import wavefile from 'wavefile';
+import fs from 'fs';
+
+const wav = new wavefile.WaveFile();
+wav.fromScratch(1, model.config.audio_encoder.sampling_rate, '32f', audio_values.data);
+fs.writeFileSync('musicgen.wav', wav.toBuffer());
+```
+
+<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/61b253b7ac5ecaae3d1efe0c/cJ9HFIDstOqJN0eGyJwlS.wav"></audio>
+
+We also released an online demo, which you can try yourself: https://huggingface.co/spaces/Xenova/musicgen-web
+
+
+<video controls src="https://cdn-uploads.huggingface.co/production/uploads/61b253b7ac5ecaae3d1efe0c/zc43B_VuUVJm4kOJPOHNh.mp4"></video>
+
+---
+
+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

@@ -0,0 +1,296 @@
+{
+  "_name_or_path": "facebook/musicgen-small",
+  "architectures": [
+    "MusicgenForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "facebook/encodec_32khz",
+    "add_cross_attention": false,
+    "architectures": [
+      "EncodecModel"
+    ],
+    "audio_channels": 1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_length_s": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_dim": 128,
+    "codebook_size": 2048,
+    "compress": 2,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dilation_growth_rate": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 128,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kernel_size": 7,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "last_kernel_size": 7,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "encodec",
+    "no_repeat_ngram_size": 0,
+    "norm_type": "weight_norm",
+    "normalize": false,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_filters": 64,
+    "num_lstm_layers": 2,
+    "num_residual_layers": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "overlap": null,
+    "pad_mode": "reflect",
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "residual_kernel_size": 3,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 32000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "target_bandwidths": [
+      2.2
+    ],
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "trim_right_ratio": 1.0,
+    "typical_p": 1.0,
+    "upsampling_ratios": [
+      8,
+      5,
+      4,
+      4
+    ],
+    "use_bfloat16": false,
+    "use_causal_conv": false,
+    "use_conv_shortcut": false
+  },
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "audio_channels": 1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 2048,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "musicgen_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 4,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 2048,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 2048
+  },
+  "is_encoder_decoder": true,
+  "model_type": "musicgen",
+  "text_encoder": {
+    "_name_or_path": "t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 3072,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "relu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "transformers_version": "4.40.0.dev0"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2048,
+  "decoder_start_token_id": 2048,
+  "do_sample": true,
+  "guidance_scale": 3.0,
+  "max_length": 1500,
+  "pad_token_id": 2048,
+  "transformers_version": "4.40.0.dev0"
+}

onnx/build_delay_pattern_mask.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84edae5bef3bfba3aad4f1e3e786dc120857cb8db136e3b9f68e4eb1a4cfeac7
+size 35360

onnx/build_delay_pattern_mask_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c988ded727c85d0c396b97cc7e79ffe5bb1a294f9c7f6e19df75d83d576d0b
+size 35379

onnx/build_delay_pattern_mask_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acc38a235d6c9499915095905bfd4b02bb4c62039f487c44084c63846d2059c
+size 52053

onnx/build_delay_pattern_mask_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4997af816452ed9c9e1c9a7f8c02cd613e235e02a179a2a0f6f3a8b0fb628e0e
+size 52092

onnx/build_delay_pattern_mask_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c988ded727c85d0c396b97cc7e79ffe5bb1a294f9c7f6e19df75d83d576d0b
+size 35379

onnx/build_delay_pattern_mask_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4997af816452ed9c9e1c9a7f8c02cd613e235e02a179a2a0f6f3a8b0fb628e0e
+size 52092

onnx/build_delay_pattern_mask_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4997af816452ed9c9e1c9a7f8c02cd613e235e02a179a2a0f6f3a8b0fb628e0e
+size 52092

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8497084fd0d4f7733ae1fa481c6d39f5130e32eff27da717fa07c6e7deb1af71
+size 1691136293

onnx/decoder_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f907283b2cc5dd902d8321f6f89013055efd471eb2d9dd145c6097f55e3390d6
+size 275515156

onnx/decoder_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50aebf05bf038e95a2ea6948f5bacf7865e36fca7e179fa5cd586f3d0ba48bae
+size 846702678

onnx/decoder_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52ff6681bc2b74ef3326584cd9e74ff6949742ca61efaf5b41ada412e1b8919
+size 424993274

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2cf8b839b2e48b480e264972931e9f6b7f7d6d1483fb00a03ad6c4bda64121
+size 1692230645

onnx/decoder_model_merged_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b258352f011dbd2717a6cb838ceccf488daca5e818e19230c2d9443d0362a1c
+size 276638222

onnx/decoder_model_merged_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9098bd6b5195626455db10198681b84b1f002033d53294d5f4df5b6faf1da365
+size 848232814

onnx/decoder_model_merged_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0784dfa87ac4cba563c01a081f22841e782bdbe91ce751b5cc955f6c499c4c6
+size 426777507

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78915f801eb40fb323fa2362ffc97bdf05099eaf21b14f5441e13813ef5eef38
+size 302373739

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dade5431ef5f3690cde7449d8e881b2d596d1ee5c6472752787d7d470d67091
+size 428422300

onnx/decoder_model_merged_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7ce852f6a9b5b4af113c6f3da41361dbdde62b5986b8da5f7f939646b498d9
+size 426777627

onnx/decoder_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b11f3bd74a4a5ef3315468d5af225c9b51d3fe2b9417d1e43682260713e3e4
+size 301252437

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fff451a7f89ae5a7e547ffa3b7933e5116f56ee928b75277d2d451418e9b09
+size 426638067

onnx/decoder_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5315e5d595e184d470e36467df93dd86bcdf1bbe5b5f5c3530fa818bdd1a691c
+size 424993394

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05501e600138f1d09220f994f924280f5b403aab503e6989acbf8ec3456e2637
+size 1486479458

onnx/decoder_with_past_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7723ccfdb919a9c5a78a6f0db57d2769abf32d2c233ea6994c00ab1b52da5355
+size 246569076

onnx/decoder_with_past_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c32661a2843568bc569f8fc66d05e5b6c5fcf4bd2ec88db898277c38e5ab30f
+size 744224406

onnx/decoder_with_past_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f079fa848c6a21ba458fee27968c7a165e0d56d4f1e81658d7b370f466e8449
+size 373572413

onnx/decoder_with_past_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dade76da136404a69a134af3f0ec0da3a3d875ad18e81ce7861cade5f808bc1
+size 269111869

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f013ec948fa4f8731c13af8fdcd24a83a5fa8e4891d5a651cfb3c11cba08c6
+size 374966081

onnx/decoder_with_past_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34151320cd6e680c391b16ffb6a22932675ac534bbffd1484769cb89d89519fb
+size 373572507

onnx/encodec_decode.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847918300a85c9a8f93333f482c5740e07c4e2599faed839bbec73fd0d588073
+size 118056304

onnx/encodec_decode_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cad95eb6dfd867cb75e2735a497beb38361a9a2e4dae385a4a51b9396ac235
+size 118056323

onnx/encodec_decode_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10aa50de680d50e13e3cb85e358bad31427c98ce9ee9cd2596af6576620a7b9
+size 59125087

onnx/encodec_decode_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bc9dd34b782aa667bbf2d83f25b31ec19db39aadc55a61e4161736c98c99bf
+size 59796619

onnx/encodec_decode_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cad95eb6dfd867cb75e2735a497beb38361a9a2e4dae385a4a51b9396ac235
+size 118056323

onnx/encodec_decode_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2a729fd329ad5390f209234c697f56c8d8f03ee6c273959b7adbccd2d4ac66
+size 59878565

onnx/encodec_decode_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5d97ab43fba9152418343efd9e61fe1eb3d00175cf8e97b124f661ac77d54b
+size 59796623

onnx/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7962c2408b03ebb37252e6d1a3179517e8c6127b9fda4e0beab84dfa09aab80
+size 438689759

onnx/text_encoder_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef68265cc3aa0cd351f33de7a57785dfc8c85d1396d567ffb2426c937383ca0
+size 146738081

onnx/text_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fdd8b8b3edc877e1ecefcabe1cad24d8d299a92ea208b1d9c732f9b63753ed
+size 219508053

onnx/text_encoder_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77494d927d25ea09e6abc8d566281b5b9cd58f39c5f89a7da60e157b0a711607
+size 110027935

onnx/text_encoder_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0a3b4e96068e2563fb15e1dd8b882934b208329eacefd8be7eb755595733f4
+size 152045969

onnx/text_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336afda84d24205409f20e71da691e5c21585e32aa86e3e38d73543ac6d481fc
+size 110443015

onnx/text_encoder_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4473292627f012bce6714118bcf22095eb4dcbf85ba140b5cb10b51de0d04c5e
+size 110027971

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "chunk_length_s": null,
+  "feature_extractor_type": "EncodecFeatureExtractor",
+  "feature_size": 1,
+  "overlap": null,
+  "padding_side": "left",
+  "padding_value": 0.0,
+  "processor_class": "MusicgenProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 32000
+}

quantize_config.json

@@ -0,0 +1,558 @@
+{
+    "fp16": {},
+    "q8": {
+        "per_model_config": {
+            "decoder_model_merged": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "If",
+                    "Less",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "decoder_model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "Less",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "text_encoder": {
+                "op_types": [
+                    "Abs",
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Gather",
+                    "Greater",
+                    "Less",
+                    "Log",
+                    "MatMul",
+                    "Min",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Relu",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "decoder_with_past_model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "encodec_decode": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Ceil",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Conv",
+                    "ConvTranspose",
+                    "Div",
+                    "Elu",
+                    "Gather",
+                    "LSTM",
+                    "Pad",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Split",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QUInt8"
+            },
+            "build_delay_pattern_mask": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Equal",
+                    "Expand",
+                    "Gather",
+                    "GreaterOrEqual",
+                    "Mul",
+                    "NonZero",
+                    "Not",
+                    "Range",
+                    "ReduceMin",
+                    "Reshape",
+                    "ScatterND",
+                    "Shape",
+                    "Slice",
+                    "Sub",
+                    "Transpose",
+                    "Trilu",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": true,
+        "reduce_range": true
+    },
+    "int8": {
+        "per_model_config": {
+            "decoder_model_merged": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "If",
+                    "Less",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "decoder_model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "Less",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "text_encoder": {
+                "op_types": [
+                    "Abs",
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Gather",
+                    "Greater",
+                    "Less",
+                    "Log",
+                    "MatMul",
+                    "Min",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Relu",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "decoder_with_past_model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            },
+            "encodec_decode": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Ceil",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Conv",
+                    "ConvTranspose",
+                    "Div",
+                    "Elu",
+                    "Gather",
+                    "LSTM",
+                    "Pad",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Split",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QInt8"
+            },
+            "build_delay_pattern_mask": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Equal",
+                    "Expand",
+                    "Gather",
+                    "GreaterOrEqual",
+                    "Mul",
+                    "NonZero",
+                    "Not",
+                    "Range",
+                    "ReduceMin",
+                    "Reshape",
+                    "ScatterND",
+                    "Shape",
+                    "Slice",
+                    "Sub",
+                    "Transpose",
+                    "Trilu",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QInt8"
+            }
+        },
+        "per_channel": false,
+        "reduce_range": false
+    },
+    "uint8": {
+        "per_model_config": {
+            "decoder_model_merged": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "If",
+                    "Less",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QUInt8"
+            },
+            "decoder_model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "Less",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Softmax",
+                    "Sqrt",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QUInt8"
+            },
+            "text_encoder": {
+                "op_types": [
+                    "Abs",
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Gather",
+                    "Greater",
+                    "Less",
+                    "Log",
+                    "MatMul",
+                    "Min",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Relu",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QUInt8"
+            },
+            "decoder_with_past_model": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Div",
+                    "Equal",
+                    "Erf",
+                    "Expand",
+                    "Gather",
+                    "MatMul",
+                    "Mul",
+                    "Pow",
+                    "Range",
+                    "ReduceMean",
+                    "Reshape",
+                    "Shape",
+                    "Softmax",
+                    "Sqrt",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QUInt8"
+            },
+            "encodec_decode": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Ceil",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Conv",
+                    "ConvTranspose",
+                    "Div",
+                    "Elu",
+                    "Gather",
+                    "LSTM",
+                    "Pad",
+                    "Reshape",
+                    "Shape",
+                    "Slice",
+                    "Split",
+                    "Squeeze",
+                    "Sub",
+                    "Transpose",
+                    "Unsqueeze"
+                ],
+                "weight_type": "QUInt8"
+            },
+            "build_delay_pattern_mask": {
+                "op_types": [
+                    "Add",
+                    "Cast",
+                    "Concat",
+                    "Constant",
+                    "ConstantOfShape",
+                    "Equal",
+                    "Expand",
+                    "Gather",
+                    "GreaterOrEqual",
+                    "Mul",
+                    "NonZero",
+                    "Not",
+                    "Range",
+                    "ReduceMin",
+                    "Reshape",
+                    "ScatterND",
+                    "Shape",
+                    "Slice",
+                    "Sub",
+                    "Transpose",
+                    "Trilu",
+                    "Unsqueeze",
+                    "Where"
+                ],
+                "weight_type": "QUInt8"
+            }
+        },
+        "per_channel": false,
+        "reduce_range": false
+    },
+    "bnb4": {
+        "block_size": 64,
+        "quant_type": 1
+    },
+    "q4": {
+        "block_size": 32,
+        "is_symmetric": true,
+        "accuracy_level": null
+    }
+}

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656