133 lines
3.0 KiB
JSON
133 lines
3.0 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 128000,
|
|
"decoder_start_token_id": 128000,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 128001,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 27648,
|
|
"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",
|
|
"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": 4096,
|
|
"max_window_layers": 28,
|
|
"model_type": "qwen3",
|
|
"no_bias": true,
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 128004,
|
|
"quantization_config": {
|
|
"bits": 4,
|
|
"checkpoint_format": "gemm",
|
|
"desc_act": false,
|
|
"group_size": 32,
|
|
"lm_head": false,
|
|
"meta": {
|
|
"act_group_aware": true,
|
|
"damp_auto_increment": 0.01,
|
|
"damp_percent": 0.05,
|
|
"mse": 0.0,
|
|
"quantizer": [
|
|
"gptqmodel:5.1.0-dev"
|
|
],
|
|
"static_groups": false,
|
|
"true_sequential": true,
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
|
"v2": false,
|
|
"v2_alpha": 0.25
|
|
},
|
|
"pack_dtype": "int32",
|
|
"pack_impl": "cpu",
|
|
"quant_method": "awq",
|
|
"sym": true,
|
|
"version": "gemm",
|
|
"zero_point": true
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": {
|
|
"factor": 8.0,
|
|
"high_freq_factor": 4.0,
|
|
"low_freq_factor": 1.0,
|
|
"original_max_position_embeddings": 8192,
|
|
"rope_type": "llama3"
|
|
},
|
|
"rope_theta": 500000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "4.57.1",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 128256
|
|
}
|