| { |
| "_name_or_path": "", |
| "accept_hidden_layer": -1, |
| "acoustic_delay": null, |
| "add_cross_attention": false, |
| "architectures": [ |
| "RaonDuplexModel" |
| ], |
| "audio_encoder_config": { |
| "_name_or_path": "", |
| "activation_function": "gelu", |
| "add_cross_attention": false, |
| "architectures": null, |
| "attention_dropout": 0.0, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "downsample_factor": 4, |
| "dtype": "bfloat16", |
| "early_stopping": false, |
| "encoder_attention_heads": 32, |
| "encoder_layers": 32, |
| "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, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 1280, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 5120, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 1500, |
| "min_length": 0, |
| "model_type": "voxtral_realtime_encoder", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 32, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "num_mel_bins": 128, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_embedding_scale": 1.0, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 151679, |
| "prefix": null, |
| "problem_type": null, |
| "projector_hidden_act": "gelu", |
| "projector_output_size": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "sampling_rate": 24000, |
| "sep_token_id": null, |
| "skip_projector": true, |
| "sliding_window": 750, |
| "suppress_tokens": null, |
| "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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| }, |
| "audio_tokenizer_config": { |
| "_frame_rate": 12.5, |
| "_name_or_path": "kyutai/mimi", |
| "add_cross_attention": false, |
| "architectures": [ |
| "MimiModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "audio_channels": 1, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "codebook_dim": 256, |
| "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, |
| "dtype": "bfloat16", |
| "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, |
| "head_dim": 64, |
| "hidden_act": "gelu", |
| "hidden_size": 512, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 2048, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "kernel_size": 7, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "last_kernel_size": 3, |
| "layer_scale_initial_scale": 0.01, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 8000, |
| "min_length": 0, |
| "model_type": "mimi", |
| "no_repeat_ngram_size": 0, |
| "norm_eps": 1e-05, |
| "normalize": false, |
| "num_attention_heads": 8, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_filters": 64, |
| "num_hidden_layers": 8, |
| "num_key_value_heads": 8, |
| "num_quantizers": 32, |
| "num_residual_layers": 1, |
| "num_return_sequences": 1, |
| "num_semantic_quantizers": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_mode": "constant", |
| "pad_token_id": 151679, |
| "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, |
| "rope_theta": 10000.0, |
| "sampling_rate": 24000, |
| "sep_token_id": null, |
| "sliding_window": 250, |
| "suppress_tokens": null, |
| "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, |
| "torchscript": false, |
| "trim_right_ratio": 1.0, |
| "typical_p": 1.0, |
| "upsample_groups": 512, |
| "upsampling_ratios": [ |
| 8, |
| 6, |
| 5, |
| 4 |
| ], |
| "use_bfloat16": true, |
| "use_cache": false, |
| "use_causal_conv": true, |
| "use_conv_shortcut": false, |
| "use_streaming": false, |
| "vector_quantization_hidden_dimension": 256 |
| }, |
| "aut_is_causal": true, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "code_predictor_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "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, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "min_length": 0, |
| "model_type": "qwen3_omni_moe_talker_code_predictor", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 16, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_code_groups": 16, |
| "num_hidden_layers": 5, |
| "num_key_value_heads": 8, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 151679, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sep_token_id": null, |
| "sliding_window": 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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": true, |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 2048 |
| }, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "depth_loss_weight": 0.25, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "duplex_bc_token_id": 151673, |
| "duplex_end_pad_token_id": 151678, |
| "duplex_pad_token_id": 151677, |
| "duplex_sil_token_id": 151672, |
| "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": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "input_adaptor_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_config": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "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": 4096, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "input_size": 5120, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "embedding_adaptor", |
| "no_repeat_ngram_size": 0, |
| "norm_eps": 1e-06, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_layers": 2, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "output_size": 4096, |
| "output_time_scale": 1.0, |
| "pad_token_id": null, |
| "post_norm_init_scale": 0.02, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "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": 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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_post_norm": true |
| }, |
| "input_num_code_groups": null, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "keys_to_ignore_at_inference": [ |
| "past_key_values" |
| ], |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "raon_duplex", |
| "no_audio_in_sil": false, |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_return_sequences": 1, |
| "num_talker_layers": 4, |
| "output_adaptor_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_config": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "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": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "input_size": 512, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "embedding_adaptor", |
| "no_repeat_ngram_size": 0, |
| "norm_eps": 1e-06, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_layers": 2, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "output_size": 4096, |
| "output_time_scale": 1, |
| "pad_token_id": null, |
| "post_norm_init_scale": 0.02, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "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": 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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_post_norm": true |
| }, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 151679, |
| "prefix": null, |
| "problem_type": null, |
| "proj_code_bias": true, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "sep_token_id": null, |
| "sequence_mode": "uta", |
| "speaker_encoder_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": null, |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "encoder_type": "ecapa_tdnn", |
| "eos_token_id": null, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "frame_rate": 12.5, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "input_size": 512, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_seconds": 10.0, |
| "min_length": 0, |
| "min_seconds": 2.0, |
| "model_type": "speaker_encoder", |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_heads": 8, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "output_size": 4096, |
| "pad_token_id": null, |
| "prefix": null, |
| "pretrained_dim": 192, |
| "pretrained_model_id": "speechbrain/spkrec-ecapa-voxceleb", |
| "problem_type": null, |
| "pruned_heads": {}, |
| "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": 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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| }, |
| "supports_audio_input": true, |
| "supports_audio_output": true, |
| "suppress_tokens": null, |
| "talker_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": null, |
| "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, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 6144, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "min_length": 0, |
| "model_type": "qwen3", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 16, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 4, |
| "num_key_value_heads": 8, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 151679, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "sep_token_id": null, |
| "sliding_window": 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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 153723 |
| }, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "text_model_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "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, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 262144, |
| "max_window_layers": 36, |
| "min_length": 0, |
| "model_type": "qwen3", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 32, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 5000000, |
| "sep_token_id": null, |
| "sliding_window": 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, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": true, |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 153723 |
| }, |
| "tf_legacy_loss": false, |
| "thinker_to_talker_intermediate_size": 6144, |
| "thinker_to_talker_pre_norm": false, |
| "thinker_to_talker_projection_mode": "mlp", |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "training_metadata": { |
| "args": { |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.95, |
| "adam_eps": 1e-08, |
| "adapter_load": null, |
| "adapters": [], |
| "add_qkv_bias": false, |
| "add_version": true, |
| "agent_template": null, |
| "apply_query_key_layer_scaling": true, |
| "architectures": "Qwen3ForCausalLM", |
| "attention_backend": "flash", |
| "attention_dropout": 0.0, |
| "attention_softmax_in_fp32": true, |
| "attn_impl": null, |
| "auto_detect_ckpt_format": true, |
| "beta": 0.1, |
| "bf16": true, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": null, |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "cached_dataset": [ |
| "dataset-is-passed-in-train-data-path" |
| ], |
| "calculate_KL": null, |
| "calculate_per_token_loss": true, |
| "center_rewards_coefficient": null, |
| "ckpt_dir": null, |
| "ckpt_format": "torch_dist", |
| "clip_grad": 1.0, |
| "columns": {}, |
| "context_parallel_size": 1, |
| "cross_entropy_fusion_impl": "native", |
| "cross_entropy_loss_fusion": true, |
| "custom_dataset_info": [], |
| "custom_register_path": [], |
| "data_seed": 42, |
| "dataloader_persistent_workers": false, |
| "dataloader_prefetch_factor": 64, |
| "dataloader_type": "external", |
| "dataset": [], |
| "dataset_num_proc": 1, |
| "dataset_shuffle": true, |
| "ddp_backend": null, |
| "ddp_timeout": 18000000, |
| "decoder_first_pipeline_num_layers": null, |
| "decoder_last_pipeline_num_layers": null, |
| "desirable_weight": 1.0, |
| "deterministic_mode": false, |
| "device_map": null, |
| "disable_bias_linear": true, |
| "distributed_backend": "nccl", |
| "distributed_timeout_minutes": 300000, |
| "download_mode": "reuse_dataset_if_exists", |
| "enable_channel_loss": false, |
| "enable_dft_loss": false, |
| "eval_interval": 1000, |
| "eval_iters": -1, |
| "exit_on_missing_checkpoint": true, |
| "exp_avg_dtype": "fp32", |
| "exp_avg_sq_dtype": "fp32", |
| "expert_model_parallel_size": 1, |
| "expert_tensor_parallel_size": 1, |
| "external_plugins": [], |
| "extra_args": { |
| "adapter_load": null, |
| "adapters": [], |
| "add_version": true, |
| "agent_template": null, |
| "architectures": "Qwen3ForCausalLM", |
| "attn_impl": null, |
| "beta": 0.1, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": null, |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "cached_dataset": [ |
| "dataset-is-passed-in-train-data-path" |
| ], |
| "calculate_KL": null, |
| "center_rewards_coefficient": null, |
| "ckpt_dir": null, |
| "columns": {}, |
| "custom_dataset_info": [], |
| "custom_register_path": [], |
| "data_seed": 42, |
| "dataloader_persistent_workers": false, |
| "dataloader_prefetch_factor": 64, |
| "dataset": [], |
| "dataset_num_proc": 1, |
| "dataset_shuffle": true, |
| "ddp_backend": null, |
| "ddp_timeout": 18000000, |
| "desirable_weight": 1.0, |
| "device_map": null, |
| "download_mode": "reuse_dataset_if_exists", |
| "enable_channel_loss": false, |
| "enable_dft_loss": false, |
| "external_plugins": [], |
| "f_divergence_type": "reverse_kl", |
| "freeze_aligner": true, |
| "freeze_llm": false, |
| "freeze_parameters": [], |
| "freeze_parameters_ratio": 0.0, |
| "freeze_parameters_regex": null, |
| "freeze_vit": true, |
| "gradient_checkpointing_kwargs": null, |
| "hqq_axis": null, |
| "hub_token": null, |
| "ignore_args_error": false, |
| "init_strategy": null, |
| "initialize_embedding": false, |
| "interleave_prob": null, |
| "label_smoothing": 0.0, |
| "layer_types": null, |
| "lazy_tokenize": false, |
| "linear_conv_kernel_dim": null, |
| "linear_key_head_dim": null, |
| "linear_num_key_heads": null, |
| "linear_num_value_heads": null, |
| "linear_value_head_dim": null, |
| "llm_architectures": null, |
| "load_args": false, |
| "load_data_args": false, |
| "load_from_cache_file": false, |
| "local_repo_path": null, |
| "logprobs": false, |
| "lora_alpha": 32, |
| "lora_bias": "none", |
| "lora_dropout": 0.05, |
| "lora_dtype": null, |
| "lora_modules": [], |
| "lora_rank": 8, |
| "loss_type": null, |
| "max_epochs": 1, |
| "max_length": 4096, |
| "max_memory": {}, |
| "max_model_len": null, |
| "max_new_tokens": null, |
| "max_pixels": null, |
| "megatron_model_meta": "MMGPTMegatronModelMeta(megatron_model_type='qwen_duplex_mcore', model_types=['qwen_duplex'], convert_mcore2hf=<function convert_mcore2hf_qwen_duplex at 0x785ff60e5800>, convert_hf2mcore=<function convert_hf2mcore_qwen_duplex at 0x785ff6077060>, model_cls=<class 'duplex_model.megatron_model.QwenDuplexGPTModel'>, convert_hf_config=<function convert_mcore2hf_qwen_duplex_config at 0x785ff60e58a0>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x785ff6058860>, visual_cls=<class 'duplex_model.megatron_model.QwenDuplexModelWrapper'>, extra_args_provider=functools.partial(<function extra_args_provider at 0x785ff60e5940>, override_kwargs={'freeze_parameters_regex': None, 'use_speaker_embedding': True}))", |
| "mlp_padding_free": false, |
| "model": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_hf", |
| "model_author": null, |
| "model_info": "ModelInfo(model_type='qwen_duplex', model_dir='/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_hf', torch_dtype=torch.bfloat16, max_model_len=None, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)", |
| "model_kwargs": {}, |
| "model_meta": "ModelMeta(model_type='qwen_duplex', model_groups=[], template='qwen3', get_function=<function get_qwen_duplex_model_and_tokenizer at 0x785ff86ec180>, model_arch=MultiModelKeys(arch_name='qwen_duplex', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['text_model'], aligner=['input_adaptor', 'output_adaptor', 'proj_code', 'audio_lm_head', 'code_predictor', 'speaker_encoder'], vision_tower=['audio_encoder', 'speaker_encoder'], generator=[]), architectures=['QwenDuplexModel'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])", |
| "model_name": null, |
| "model_revision": null, |
| "model_type": "qwen_duplex", |
| "modules_to_save": [], |
| "mrope_interleaved": false, |
| "new_special_tokens": [], |
| "norm_bbox": null, |
| "num_beams": 1, |
| "num_labels": null, |
| "original_max_position_embeddings": null, |
| "packing": true, |
| "packing_length": 4096, |
| "padded_vocab_size": 153723, |
| "padding_free": true, |
| "padding_side": "right", |
| "partial_rotary_factor": null, |
| "problem_type": null, |
| "quant_bits": null, |
| "quant_method": null, |
| "ref_adapter_load": null, |
| "ref_load": null, |
| "reference_free": false, |
| "remove_unused_columns": false, |
| "repetition_penalty": null, |
| "response_prefix": null, |
| "rlhf_type": null, |
| "rope_scaling": null, |
| "rpo_alpha": null, |
| "sequence_parallel_size": 1, |
| "shuffle_buffer_size": 1000, |
| "split_dataset_ratio": 0.0, |
| "stop_words": [], |
| "stopping_strategy": "first_exhausted", |
| "stream": false, |
| "streaming": false, |
| "strict": false, |
| "system": null, |
| "target_modules": [ |
| "all-linear" |
| ], |
| "target_regex": null, |
| "task_type": "causal_lm", |
| "temperature": null, |
| "template": "qwen3", |
| "template_backend": "swift", |
| "top_k": null, |
| "top_logprobs": null, |
| "top_p": null, |
| "torch_dtype": "bfloat16", |
| "train_type": "full", |
| "trainable_parameters": [], |
| "trainable_parameters_regex": null, |
| "truncation_strategy": "delete", |
| "tuner_backend": "peft", |
| "undesirable_weight": 1.0, |
| "use_chat_template": true, |
| "use_hf": false, |
| "use_rslora": false, |
| "use_shared_expert_gate": false, |
| "use_swift_lora": false, |
| "val_dataset": [], |
| "val_dataset_shuffle": false, |
| "vit_gradient_checkpointing": false |
| }, |
| "extra_megatron_kwargs": {}, |
| "f_divergence_type": "reverse_kl", |
| "ffn_hidden_size": 12288, |
| "finetune": true, |
| "fp16": false, |
| "fp8_amax_compute_algo": "max", |
| "fp8_amax_history_len": 1024, |
| "fp8_format": null, |
| "fp8_param_gather": false, |
| "fp8_recipe": "delayed", |
| "freeze_aligner": true, |
| "freeze_llm": false, |
| "freeze_parameters": [], |
| "freeze_parameters_ratio": 0.0, |
| "freeze_parameters_regex": null, |
| "freeze_vit": true, |
| "global_batch_size": 64, |
| "global_world_size": 64, |
| "gradient_checkpointing_kwargs": null, |
| "group_query_attention": true, |
| "hidden_dropout": 0.0, |
| "hidden_size": 4096, |
| "hqq_axis": null, |
| "hub": "<class 'swift.hub.hub.MSHub'>", |
| "hub_token": null, |
| "ignore_args_error": false, |
| "init_strategy": null, |
| "initialize_embedding": false, |
| "interleave_prob": null, |
| "kv_channels": 128, |
| "kv_lora_rank": 32, |
| "label_smoothing": 0.0, |
| "layer_types": null, |
| "lazy_tokenize": false, |
| "linear_conv_kernel_dim": null, |
| "linear_key_head_dim": null, |
| "linear_num_key_heads": null, |
| "linear_num_value_heads": null, |
| "linear_value_head_dim": null, |
| "llm_architectures": null, |
| "load": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_mcore", |
| "load_args": false, |
| "load_data_args": false, |
| "load_from_cache_file": false, |
| "local_rank": 0, |
| "local_repo_path": null, |
| "local_world_size": 8, |
| "log_interval": 1, |
| "log_memory_to_tensorboard": true, |
| "log_params_norm": false, |
| "log_throughput": true, |
| "log_timers_to_tensorboard": true, |
| "log_validation_ppl_to_tensorboard": false, |
| "logging_level": null, |
| "logprobs": false, |
| "lora_alpha": 32, |
| "lora_bias": "none", |
| "lora_dropout": 0.05, |
| "lora_dtype": null, |
| "lora_modules": [], |
| "lora_rank": 8, |
| "loss_scale": "default", |
| "loss_type": null, |
| "lr": 3e-06, |
| "lr_decay_iters": null, |
| "lr_decay_style": "cosine", |
| "lr_warmup_fraction": 0.05, |
| "lr_warmup_iters": 0, |
| "main_grads_dtype": "fp32", |
| "main_params_dtype": "fp32", |
| "manual_gc": false, |
| "manual_gc_interval": 0, |
| "max_epochs": 1, |
| "max_length": 4096, |
| "max_memory": {}, |
| "max_model_len": null, |
| "max_new_tokens": null, |
| "max_pixels": null, |
| "max_position_embeddings": 262144, |
| "megatron_model_meta": "MMGPTMegatronModelMeta(megatron_model_type='qwen_duplex_mcore', model_types=['qwen_duplex'], convert_mcore2hf=<function convert_mcore2hf_qwen_duplex at 0x785ff60e5800>, convert_hf2mcore=<function convert_hf2mcore_qwen_duplex at 0x785ff6077060>, model_cls=<class 'duplex_model.megatron_model.QwenDuplexGPTModel'>, convert_hf_config=<function convert_mcore2hf_qwen_duplex_config at 0x785ff60e58a0>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x785ff6058860>, visual_cls=<class 'duplex_model.megatron_model.QwenDuplexModelWrapper'>, extra_args_provider=functools.partial(<function extra_args_provider at 0x785ff60e5940>, override_kwargs={'freeze_parameters_regex': None, 'use_speaker_embedding': True}))", |
| "micro_batch_size": 1, |
| "microbatch_group_size_per_virtual_pipeline_stage": null, |
| "min_lr": 3e-07, |
| "mlp_padding_free": false, |
| "model": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_hf", |
| "model_author": null, |
| "model_dir": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_hf", |
| "model_info": "ModelInfo(model_type='qwen_duplex', model_dir='/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_hf', torch_dtype=torch.bfloat16, max_model_len=None, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)", |
| "model_kwargs": {}, |
| "model_meta": "ModelMeta(model_type='qwen_duplex', model_groups=[], template='qwen3', get_function=<function get_qwen_duplex_model_and_tokenizer at 0x785ff86ec180>, model_arch=MultiModelKeys(arch_name='qwen_duplex', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['text_model'], aligner=['input_adaptor', 'output_adaptor', 'proj_code', 'audio_lm_head', 'code_predictor', 'speaker_encoder'], vision_tower=['audio_encoder', 'speaker_encoder'], generator=[]), architectures=['QwenDuplexModel'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])", |
| "model_name": null, |
| "model_revision": null, |
| "model_suffix": "iter_0025000_hf", |
| "model_type": "qwen_duplex", |
| "modules_to_save": [], |
| "moe_aux_loss_coeff": 0.0, |
| "moe_enable_deepep": false, |
| "moe_expert_capacity_factor": null, |
| "moe_ffn_hidden_size": null, |
| "moe_grouped_gemm": false, |
| "moe_layer_freq": "1", |
| "moe_layer_recompute": false, |
| "moe_pad_expert_input_to_capacity": false, |
| "moe_permute_fusion": false, |
| "moe_router_bias_update_rate": 0.001, |
| "moe_router_dtype": "fp32", |
| "moe_router_enable_expert_bias": false, |
| "moe_router_load_balancing_type": "aux_loss", |
| "moe_router_pre_softmax": false, |
| "moe_router_score_function": "softmax", |
| "moe_router_topk": 2, |
| "moe_router_topk_scaling_factor": null, |
| "moe_shared_expert_intermediate_size": null, |
| "moe_shared_expert_overlap": false, |
| "moe_token_dispatcher_type": null, |
| "moe_token_drop_policy": null, |
| "moe_z_loss_coeff": null, |
| "mrope_interleaved": false, |
| "mrope_section": null, |
| "multi_latent_attention": false, |
| "new_special_tokens": [], |
| "no_bias_dropout_fusion": false, |
| "no_bias_swiglu_fusion": false, |
| "no_gradient_accumulation_fusion": false, |
| "no_initialization": true, |
| "no_load_optim": false, |
| "no_load_rng": false, |
| "no_log_learning_rate_to_tensorboard": false, |
| "no_masked_softmax_fusion": false, |
| "no_rope_fusion": false, |
| "no_save_optim": false, |
| "no_save_rng": false, |
| "norm_bbox": null, |
| "norm_epsilon": 1e-06, |
| "normalization": "RMSNorm", |
| "num_attention_heads": 32, |
| "num_beams": 1, |
| "num_experts": null, |
| "num_labels": null, |
| "num_layers": 36, |
| "num_layers_per_virtual_pipeline_stage": null, |
| "num_query_groups": 8, |
| "num_virtual_stages_per_pipeline_rank": null, |
| "num_workers": 16, |
| "optimizer": "adam", |
| "optimizer_cpu_offload": false, |
| "optimizer_offload_fraction": 1.0, |
| "original_max_position_embeddings": null, |
| "overlap_grad_reduce": false, |
| "overlap_param_gather": false, |
| "packing": true, |
| "packing_length": 4096, |
| "padded_vocab_size": 153723, |
| "padding_free": true, |
| "padding_side": "right", |
| "partial_rotary_factor": null, |
| "pipeline_model_parallel_layout": null, |
| "pipeline_model_parallel_size": 1, |
| "position_embedding_type": "rope", |
| "problem_type": null, |
| "q_lora_rank": null, |
| "qk_head_dim": 128, |
| "qk_layernorm": true, |
| "qk_pos_emb_head_dim": 64, |
| "quant_bits": null, |
| "quant_method": null, |
| "rank": 0, |
| "recompute_granularity": "selective", |
| "recompute_method": null, |
| "recompute_modules": [ |
| "core_attn" |
| ], |
| "recompute_num_layers": null, |
| "ref_adapter_load": null, |
| "ref_load": null, |
| "reference_free": false, |
| "remove_unused_columns": false, |
| "repetition_penalty": null, |
| "response_prefix": null, |
| "rlhf_type": null, |
| "rope_scaling": null, |
| "rotary_base": 5000000, |
| "rotary_interleaved": false, |
| "rotary_percent": 1.0, |
| "rpo_alpha": null, |
| "save": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-ft-v4-s1-fa-res25k-20260401/v0-20260401-135515", |
| "save_interval": 1000, |
| "seed": 7, |
| "seq_length": 4096, |
| "sequence_parallel": false, |
| "sequence_parallel_size": 1, |
| "sgd_momentum": 0.9, |
| "shuffle_buffer_size": 1000, |
| "split_dataset_ratio": 0.0, |
| "stop_words": [], |
| "stopping_strategy": "first_exhausted", |
| "stream": false, |
| "streaming": false, |
| "strict": false, |
| "swiglu": true, |
| "system": null, |
| "target_modules": [ |
| "all-linear" |
| ], |
| "target_regex": null, |
| "task_type": "causal_lm", |
| "temperature": null, |
| "template": "qwen3", |
| "template_backend": "swift", |
| "tensor_model_parallel_size": 1, |
| "tensorboard_dir": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-ft-v4-s1-fa-res25k-20260401/v0-20260401-135515/runs", |
| "tensorboard_log_interval": 1, |
| "tensorboard_queue_size": 50, |
| "top_k": null, |
| "top_logprobs": null, |
| "top_p": null, |
| "torch_dtype": "bfloat16", |
| "tp_comm_overlap": false, |
| "train_iters": 5000, |
| "train_type": "full", |
| "trainable_parameters": [], |
| "trainable_parameters_regex": null, |
| "transformer_impl": "transformer_engine", |
| "truncation_strategy": "delete", |
| "tuner_backend": "peft", |
| "undesirable_weight": 1.0, |
| "untie_embeddings_and_output_weights": true, |
| "use_chat_template": true, |
| "use_cpu_initialization": false, |
| "use_distributed_optimizer": true, |
| "use_flash_attn": true, |
| "use_hf": false, |
| "use_precision_aware_optimizer": false, |
| "use_rslora": false, |
| "use_shared_expert_gate": false, |
| "use_swift_lora": false, |
| "val_dataset": [], |
| "val_dataset_shuffle": false, |
| "vit_gradient_checkpointing": false, |
| "wandb_exp_name": null, |
| "wandb_project": null, |
| "wandb_save_dir": null, |
| "weight_decay": 0.1 |
| }, |
| "checkpoint_iter": 5000, |
| "recipe_trace": "00 [current] /usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-ft-v4-s1-fa-res25k-20260401/v0-20260401-135515\n01 [load] /usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-duplex-resume-20k-20260401/v0-20260401-045855/iter_0025000_mcore", |
| "training_run_path": "/usrs/model-team/exps/sehun/duplex/8B-V2-voxtral-ft-v4-s1-fa-res25k-20260401/v0-20260401-135515" |
| }, |
| "transformers_version": "4.57.3", |
| "typical_p": 1.0, |
| "use_backchannel_token": true, |
| "use_bfloat16": false, |
| "use_duplex_end_pad": true, |
| "use_inline_text_prediction": false, |
| "use_sil_token": true, |
| "auto_map": { |
| "AutoConfig": "configuration_raon.RaonDuplexConfig", |
| "AutoModel": "modeling_raon.RaonDuplexModel" |
| } |
| } |
|
|
