Moss-Saudi-2 / config.json
Rabe3's picture
Upload Moss-Saudi-2 LoRA and merged weights
a728b62 verified
Raw
History Blame Contribute Delete
7.01 kB
{
"architectures": [
"MossTTSLocalModel"
],
"attn_implementation": "flash_attention_2",
"audio_assistant_gen_slot_token_id": 151656,
"audio_assistant_slot_token_id": 151656,
"audio_codebook_sizes": [
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024,
1024
],
"audio_end_token_id": 151670,
"audio_pad_code": 1024,
"audio_pad_token_id": 1024,
"audio_start_token_id": 151669,
"audio_tokenizer_name_or_path": "OpenMOSS-Team/MOSS-Audio-Tokenizer-v2",
"audio_user_slot_token_id": 151654,
"audio_vocab_size": 1024,
"auto_map": {
"AutoConfig": "configuration_moss_tts.MossTTSLocalConfig",
"AutoModel": "modeling_moss_tts.MossTTSLocalModel",
"AutoProcessor": "processing_moss_tts.MossTTSLocalProcessor"
},
"dtype": "bfloat16",
"gpt2_config": {
"activation_function": "silu",
"add_cross_attention": false,
"attn_pdrop": 0.0,
"bos_token_id": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"embd_pdrop": 0.0,
"eos_token_id": 151645,
"finetuning_task": null,
"initializer_range": 0.02,
"is_decoder": false,
"layer_norm_epsilon": 1e-06,
"model_type": "gpt2",
"n_ctx": 10240,
"n_embd": 2560,
"n_head": 32,
"n_inner": 9728,
"n_layer": 1,
"n_positions": 10240,
"pad_token_id": null,
"position_embedding_type": "rope",
"prefix": null,
"pruned_heads": {},
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.0,
"rope_base": 1000000.0,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"sep_token_id": null,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": null,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"torchscript": false,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 151936
},
"hidden_size": 2560,
"im_end_token_id": 151645,
"im_start_token_id": 151644,
"initializer_range": 0.02,
"language_config": {
"add_cross_attention": false,
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151643,
"finetuning_task": null,
"gradient_checkpointing_use_reentrant": false,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"is_decoder": false,
"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"
],
"max_position_embeddings": 32768,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"prefix": null,
"pruned_heads": {},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sep_token_id": null,
"sliding_window": null,
"task_specific_params": null,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"torchscript": false,
"use_bfloat16": false,
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
},
"local_hidden_size": 2560,
"local_text_head_mode": "binary",
"local_transformer_attn_implementation": "flash_attention_2",
"local_transformer_layers": 1,
"model_type": "moss_tts_local",
"n_vq": 12,
"pad_token_id": 151643,
"processor_class": "MossTTSLocalProcessor",
"qwen3_config": {
"add_cross_attention": false,
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151643,
"finetuning_task": null,
"gradient_checkpointing_use_reentrant": false,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"is_decoder": false,
"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"
],
"max_position_embeddings": 32768,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"prefix": null,
"pruned_heads": {},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sep_token_id": null,
"sliding_window": null,
"task_specific_params": null,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"torchscript": false,
"use_bfloat16": false,
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
},
"sampling_rate": 48000,
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"use_static_local_kv_cache": true,
"vocab_size": 151936
}