| { |
| "architectures": [ |
| "ClvpModelForConditionalGeneration" |
| ], |
| "decoder_config": { |
| "activation_function": "gelu_new", |
| "add_cross_attention": false, |
| "attention_dropout": 0.1, |
| "bos_token_id": 97, |
| "decoder_fixing_codes": [ |
| 83, |
| 45, |
| 45, |
| 248 |
| ], |
| "embd_pdrop": 0.1, |
| "eos_token_id": 98, |
| "feature_size": 80, |
| "hidden_size": 128, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "max_position_embeddings": 30, |
| "max_text_tokens": 30, |
| "model_type": "clvp_decoder", |
| "n_inner": null, |
| "num_attention_heads": 2, |
| "num_hidden_layers": 1, |
| "num_mel_attn_blocks": 6, |
| "pad_token_id": null, |
| "relative_attention_max_distance": 16, |
| "relative_attention_num_buckets": 4, |
| "resid_pdrop": 0.1, |
| "summary_activation": null, |
| "summary_first_dropout": 0.1, |
| "summary_proj_to_labels": true, |
| "summary_type": "cls_index", |
| "summary_use_proj": true, |
| "use_attention_bias": true, |
| "use_cache": true, |
| "vocab_size": 50 |
| }, |
| "dtype": "float32", |
| "initializer_factor": 1.0, |
| "logit_scale_init_value": 2.6592, |
| "model_type": "clvp", |
| "projection_dim": 16, |
| "speech_config": { |
| "attention_dropout": 0.1, |
| "bos_token_id": 49, |
| "dropout": 0.1, |
| "eos_token_id": 49, |
| "hidden_act": "gelu", |
| "hidden_size": 128, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "layer_norm_eps": 1e-05, |
| "model_type": "clvp_encoder", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 2, |
| "pad_token_id": null, |
| "projection_dim": 16, |
| "summary_type": "mean", |
| "use_attention_bias": false, |
| "use_rotary_embedding": true, |
| "vocab_size": 300 |
| }, |
| "text_config": { |
| "attention_dropout": 0.1, |
| "bos_token_id": 1, |
| "dropout": 0.1, |
| "eos_token_id": 0, |
| "hidden_act": "gelu", |
| "hidden_size": 128, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "layer_norm_eps": 1e-05, |
| "model_type": "clvp_encoder", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 2, |
| "pad_token_id": null, |
| "projection_dim": 16, |
| "summary_type": "mean", |
| "use_attention_bias": false, |
| "use_rotary_embedding": true, |
| "vocab_size": 256 |
| }, |
| "transformers_version": "5.16.0.dev0" |
| } |
|
|
