MOSS-TTSD-NF4 / config.json
groxaxo's picture
Add NF4 quantized weights (5.96 GiB)
755ddc3 verified
{
"architectures": [
"MossTTSDelayModel"
],
"audio_assistant_delay_slot_token_id": 151662,
"audio_assistant_gen_slot_token_id": 151656,
"audio_end_token_id": 151653,
"audio_pad_code": 1024,
"audio_start_token_id": 151652,
"audio_user_slot_token_id": 151654,
"audio_vocab_size": 1024,
"auto_map": {
"AutoConfig": "configuration_moss_tts.MossTTSDelayConfig",
"AutoModel": "modeling_moss_tts.MossTTSDelayModel"
},
"dtype": "bfloat16",
"hidden_size": 4096,
"im_end_token_id": 151645,
"im_start_token_id": 151644,
"initializer_range": 0.02,
"language_config": {
"_name_or_path": "Qwen/Qwen3-8B",
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"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": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 155648
},
"model_type": "moss_tts_delay",
"n_vq": 16,
"pad_token_id": 151643,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"sampling_rate": 24000,
"transformers_version": "5.3.0",
"vocab_size": 155648
}