musicgen-stereo-medium / config.json
reach-vb's picture
reach-vb HF staff
Add HF Weights (#1)
c822fdd
{
"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": 2,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 2048,
"chunk_size_feed_forward": 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": 6144,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 1536,
"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": 24,
"num_beam_groups": 1,
"num_beams": 1,
"num_codebooks": 8,
"num_hidden_layers": 48,
"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
},
"torch_dtype": "float16",
"transformers_version": "4.36.0.dev0"
}