Qwen-Audio-nf4 / config.json
Ostixe360's picture
Upload model
e218400 verified
{
"_name_or_path": "Qwen/Qwen-Audio",
"architectures": [
"QWenLMHeadModel"
],
"attn_dropout_prob": 0.0,
"audio": {
"add_audio_bos_eos_token": true,
"audio_start_id": 155163,
"avg_pool": true,
"n_ctx": 1500,
"n_head": 20,
"n_layer": 32,
"n_mels": 80,
"n_state": 1280,
"output_dim": 4096
},
"auto_map": {
"AutoConfig": "Qwen/Qwen-Audio--configuration_qwen.QWenConfig",
"AutoModelForCausalLM": "Qwen/Qwen-Audio--modeling_qwen.QWenLMHeadModel"
},
"bf16": true,
"emb_dropout_prob": 0.0,
"fp16": false,
"fp32": false,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 22016,
"kv_channels": 128,
"layer_norm_epsilon": 1e-06,
"max_position_embeddings": 2048,
"model_type": "qwen",
"no_bias": true,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"onnx_safe": null,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": false,
"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"
},
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"scale_attn_weights": true,
"seq_length": 2048,
"softmax_in_fp32": false,
"tie_word_embeddings": false,
"tokenizer_type": "QWenTokenizer",
"torch_dtype": "bfloat16",
"transformers_version": "4.40.1",
"use_cache": true,
"use_cache_kernel": false,
"use_cache_quantization": false,
"use_dynamic_ntk": true,
"use_flash_attn": true,
"use_logn_attn": true,
"vocab_size": 155947
}