InteractiveOmni-8B / config.json
sensefvg's picture
upload initial model
b3f3294 verified
{
"_commit_hash": null,
"_name_or_path": "InteractiveOmni",
"architectures": [
"InteractiveOmniModel"
],
"auto_map": {
"AutoConfig": "configuration_interactiveomni.InteractiveOmniConfig",
"AutoModel": "modeling_interactiveomni.InteractiveOmniModel",
"AutoModelForCausalLM": "modeling_interactiveomni.InteractiveOmniModel"
},
"audio_config": {
"_name_or_path": "openai/whisper-large-v3",
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": false,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": [
220,
50257
],
"bos_token_id": 50257,
"classifier_proj_size": 256,
"d_model": 1280,
"decoder_attention_heads": 20,
"decoder_ffn_dim": 5120,
"decoder_layerdrop": 0.0,
"decoder_layers": 32,
"decoder_start_token_id": 50258,
"dropout": 0.0,
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"eos_token_id": 50257,
"init_std": 0.02,
"is_encoder_decoder": true,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"max_length": 448,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 128,
"pad_token_id": 50256,
"scale_embedding": false,
"torch_dtype": "float16",
"transformers_version": "4.36.0.dev0",
"use_cache": true,
"use_weighted_layer_sum": false,
"vocab_size": 51866
},
"audio_preprocessor_config": {
"chunk_length": 30,
"feature_extractor_type": "WhisperFeatureExtractor",
"feature_size": 128,
"hop_length": 160,
"n_fft": 400,
"n_samples": 480000,
"nb_max_frames": 3000,
"padding_side": "right",
"padding_value": 0.0,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"sampling_rate": 16000
},
"downsample_ratio": 0.25,
"dynamic_image_size": true,
"force_image_size": 448,
"llm_config": {
"_name_or_path": "Qwen/Qwen3-8B",
"add_cross_attention": false,
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_implementation": "flash_attention_2",
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bias": false,
"bos_token_id": 151643,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 151645,
"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
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 40960,
"max_window_layers": 40,
"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": {
"factor": 2.0,
"type": "dynamic"
},
"rope_theta": 1000000.0,
"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,
"torch_dtype": "bfloat16",
"torchscript": false,
"transformers_version": "4.51.0",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151968
},
"max_dynamic_patch": 12,
"min_dynamic_patch": 1,
"model_type": "interactiveomni",
"pad2square": false,
"ps_version": "v2",
"select_layer": -1,
"template": "interactiveomni_template",
"torch_dtype": "bfloat16",
"transformers_version": null,
"use_backbone_lora": 0,
"use_llm_lora": 0,
"use_thumbnail": true,
"vision_config": {
"_name_or_path": "OpenGVLab/InternViT-300M-448px",
"add_cross_attention": false,
"architectures": [
"InternVisionModel"
],
"auto_map": {
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
"AutoModel": "modeling_intern_vit.InternVisionModel"
},
"attention_dropout": 0.0,
"drop_path_rate": 0.1,
"dropout": 0.0,
"hidden_act": "gelu",
"hidden_size": 1024,
"image_size": 448,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-06,
"model_type": "intern_vit_6b",
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"qk_normalization": false,
"qkv_bias": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"use_flash_attn": true
},
"flow_config": {
"_attn_implementation_internal": null,
"_commit_hash": null,
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"CausalMaskedDiffWithXvec"
],
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_config": {
"cfm_params": {
"inference_cfg_rate": 0.7,
"reg_loss_type": "l1",
"sigma_min": 1e-06,
"solver": "euler",
"t_scheduler": "cosine",
"training_cfg_rate": 0.2
},
"estimator_config": {
"act_fn": "gelu",
"attention_head_dim": 64,
"causal": true,
"channels": [
256
],
"dropout": 0.0,
"in_channels": 320,
"n_blocks": 4,
"num_heads": 8,
"num_mid_blocks": 12,
"out_channels": 80
},
"in_channels": 240,
"n_spks": 1,
"spk_emb_dim": 80
},
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_config": {
"attention_dropout_rate": 0.1,
"attention_heads": 8,
"dropout_rate": 0.1,
"input_layer": "linear",
"input_size": 512,
"linear_units": 2048,
"macaron_style": false,
"normalize_before": true,
"num_blocks": 6,
"output_size": 512,
"pos_enc_layer_type": "rel_pos_espnet",
"positional_dropout_rate": 0.1,
"selfattention_layer_type": "rel_selfattn",
"use_cnn_module": 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,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"input_frame_rate": 25,
"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,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"only_mask_loss": true,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"output_size": 80,
"output_type": "mel",
"pad_token_id": null,
"pre_lookahead_len": 3,
"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,
"spk_embed_dim": 192,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"token_mel_ratio": 2,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": null,
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 6561
},
"hifigan_config": {
"_attn_implementation_internal": null,
"_commit_hash": null,
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"HiFTGenerator"
],
"audio_limit": 0.99,
"bad_words_ids": null,
"base_channels": 512,
"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,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"f0_predictor_config": {
"cond_channels": 512,
"in_channels": 80,
"num_class": 1
},
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"in_channels": 80,
"is_decoder": false,
"is_encoder_decoder": false,
"istft_params": {
"hop_len": 4,
"n_fft": 16
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"lrelu_slope": 0.1,
"max_length": 20,
"min_length": 0,
"nb_harmonics": 8,
"no_repeat_ngram_size": 0,
"nsf_alpha": 0.1,
"nsf_sigma": 0.003,
"nsf_voiced_threshold": 10,
"num_beam_groups": 1,
"num_beams": 1,
"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,
"resblock_dilation_sizes": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"resblock_kernel_sizes": [
3,
7,
11
],
"return_dict": true,
"return_dict_in_generate": false,
"sampling_rate": 24000,
"sep_token_id": null,
"source_resblock_dilation_sizes": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"source_resblock_kernel_sizes": [
7,
7,
11
],
"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,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": null,
"typical_p": 1.0,
"upsample_kernel_sizes": [
16,
11,
7
],
"upsample_rates": [
8,
5,
3
],
"use_bfloat16": false
},
"voicelm_config": {
"_attn_implementation_internal": null,
"_commit_hash": null,
"_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,
"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,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_normalized_loss": true,
"length_penalty": 1.0,
"llm_config": {
"add_cross_attention": false,
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 151643,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 151643,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 896,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 4864,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 32768,
"max_window_layers": 24,
"min_length": 0,
"model_type": "qwen2",
"no_repeat_ngram_size": 0,
"num_attention_heads": 14,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"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_theta": 1000000.0,
"sep_token_id": null,
"sliding_window": 32768,
"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,
"torch_dtype": "bfloat16",
"torchscript": false,
"transformers_version": "4.37.2",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": false,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 151936
},
"llm_input_size": 896,
"llm_output_size": 896,
"lsm_weight": 0,
"max_length": 20,
"min_length": 0,
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"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,
"sampling_config": {
"tau_r": 0.1,
"top_k": 15,
"top_p": 0.7,
"win_size": 10
},
"sep_token_id": null,
"speech_token_size": 6561,
"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,
"torch_dtype": null,
"torchscript": false,
"transformers_version": null,
"typical_p": 1.0,
"use_bfloat16": false
}
}