Ming-Lite-Omni-Preview / config.json
LandyGuo
First model version
e92022a
{
"_name_or_path": ".",
"architectures": [
"BailingMMNativeForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_bailingmm.BailingMMConfig"
},
"audio_config": {
"audio_decoder_type": null,
"audio_encoder_config_sanm": {
"attention_dropout_rate": 0.1,
"attention_heads": 4,
"dropout_rate": 0.1,
"input_layer": "pe",
"input_size": 560,
"kernel_size": 11,
"linear_units": 2048,
"normalize_before": true,
"num_blocks": 50,
"output_size": 512,
"pos_enc_class": "SinusoidalPositionEncoder",
"positional_dropout_rate": 0.1,
"sanm_shfit": 0,
"selfattention_layer_type": "sanm"
},
"audio_encoder_output_size": 512,
"audio_id_shift": null,
"audio_wav_frontend_config_sanm": {},
"ds_conv_type": "conv",
"ds_kernel_size": 1,
"ds_stride": 1,
"model_type": "bailingmm",
"norm_query_embeds": true,
"use_audio_bpe_token": false,
"vocab_size_audio": 0
},
"auto_map": {
"AutoConfig": "configuration_bailingmm.BailingMMConfig"
},
"llm_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"BailingMoeForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_bailing_moe.BailingMoeConfig",
"AutoModel": "modeling_bailing_moe.BailingMoeModel",
"AutoModelForCausalLM": "modeling_bailing_moe.BailingMoeForCausalLM",
"AutoModelForTokenClassification": "modeling_bailing_moe.BailingMoeForTokenClassification"
},
"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,
"embedding_dropout": 0.0,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 126081,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"first_k_dense_replace": 0,
"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"
},
"image_patch_token": 126346,
"initializer_range": 0.006,
"intermediate_size": 5632,
"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": 28,
"min_length": 0,
"model_type": "bailing_moe",
"moe_intermediate_size": 1408,
"multi_gate": true,
"no_repeat_ngram_size": 0,
"norm_head": true,
"norm_softmax": false,
"norm_topk_prob": true,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_experts": 64,
"num_experts_per_tok": 6,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"num_return_sequences": 1,
"num_shared_experts": 2,
"output_attentions": false,
"output_dropout": 0.0,
"output_hidden_states": false,
"output_router_logits": false,
"output_scores": false,
"pad_token_id": 126081,
"prefix": null,
"pretraining_tp": 1,
"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": 600000,
"sep_token_id": null,
"sliding_window": 4096,
"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,
"typical_p": 1.0,
"use_bfloat16": false,
"use_bias": false,
"use_cache": true,
"use_qkv_bias": false,
"use_sliding_window": false,
"vocab_size": 126464
},
"mlp_depth": 2,
"model_type": "bailingmm",
"talker_config": {
"_name_or_path": "./talker",
"add_cross_attention": false,
"architectures": null,
"audio_vocab_size": 32768,
"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_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "",
"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,
"pretrained_model_path": null,
"problem_type": null,
"pruned_heads": {},
"qa_model_hidden_size": 2048,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"s3bpe_tokenizer": null,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"text_vocab_size": 151677,
"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,
"vocab_size": 184445,
"vp_feature_size": 192,
"vp_kernel_size": 1,
"vp_stride": 1
},
"torch_dtype": "float32",
"transformers_version": "4.45.0",
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"Qwen2_5_VisionTransformer"
],
"auto_map": {
"AutoConfig": "configuration_qwen2_5_vit.Qwen2_5_VLVisionConfig",
"AutoModel": "qwen2_5_vit.Qwen2_5_VisionTransformer"
},
"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,
"depth": 32,
"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,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"in_channels": 3,
"in_chans": 3,
"intermediate_size": 3456,
"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": "qwen2_5_vit",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 16,
"num_return_sequences": 1,
"out_hidden_size": 8192,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"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,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"temporal_patch_size": 2,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"tokens_per_second": 2,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "bfloat16",
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"window_size": 112
}
}